Jump to Content
Zhifeng Chen

Zhifeng Chen

Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Preview abstract The development of language models have moved from encoder-decoder to decoder-only designs. In addition, the common knowledge has it that the two most popular multimodal tasks, the generative and contrastive tasks, tend to conflict with one another, are hard to accommodate in one architecture, and further need complex adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is able to accommodate contrastive and generative learning by a novel two-pass approach on the text decoder. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Furthermore, the same architecture enables straightforward extensions to open-vocabulary object detection and video-language tasks. The model tackles a diverse range of tasks, while being modest in capacity. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models. It shows very competitive results on VQA and Video Captioning, especially considering its capacity. Ablations confirm the flexibility and advantages of our approach. View details
    Noise2Music: Text-conditioned Music Generation with Diffusion Models
    Qingqing Huang
    Daniel S. Park
    Tao Wang
    Nanxin Chen
    Zhengdong Zhang
    Zhishuai Zhang
    Jiahui Yu
    Christian Frank
    William Chan
    Wei Han
    (2023)
    Preview abstract We introduce Noise2Music, where a series of diffusion models are trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one in which it is a spectrogram and the other in which it is audio with lower fidelity. We find that the generated audio is able to faithfully reflect key elements of the text prompt such as genre, mood, tempo and instruments. Language models play a key role in this story---they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. View details
    Sparsely Activated Language Models are Efficient In-Context Learners
    Adams Yu
    Barret Richard Zoph
    Dmitry (Dima) Lepikhin
    Emma Wang
    Kun Zhang
    Liam B. Fedus
    Maarten Paul Bosma
    Marie Pellat
    Maxim Krikun
    Nan Du
    Simon Tong
    Tao Wang
    Toju Duke
    Yuanzhong Xu
    Zongwei Zhou
    (2022)
    Preview abstract Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong performance on few-shot learning. However, training these large dense models require significant amounts of computing resources. In this paper, we develop a family of sparsely activated mixture-of-expert language models named \glam (\textbf{G}eneralist \textbf{La}nguage \textbf{M}odel), which can have many more parameters but require significant less training cost than dense models. The largest \glam has 1.2 trillion parameters, which is approximately 7x larger than GPT-3 but can be trained more efficiently. With only 1/3 of energy consumption to train GPT-3, \glam achieves better overall performance on 29 zero-shot and one-shot NLP tasks. For example, \glam gets 75.0\% one-shot exact match accuracy on the TriviaQA test server, a significant improvement over 68.0\% obtained by GPT-3. View details
    LaMDA: Language Models for Dialog Applications
    Aaron Daniel Cohen
    Alena Butryna
    Alicia Jin
    Apoorv Kulshreshtha
    Ben Zevenbergen
    Chung-ching Chang
    Cosmo Du
    Daniel De Freitas Adiwardana
    Dehao Chen
    Dmitry (Dima) Lepikhin
    Erin Hoffman-John
    Hongrae Lee
    Igor Krivokon
    James Qin
    Jamie Hall
    Joe Fenton
    Johnny Soraker
    Lora Mois Aroyo
    Maarten Paul Bosma
    Marc Joseph Pickett
    Marcelo Amorim Menegali
    Marian Croak
    Maxim Krikun
    Meredith Ringel Morris
    Noam Shazeer
    Rachel Bernstein
    Ravi Rajakumar
    Ray Kurzweil
    Romal Thoppilan
    Steven Zheng
    Taylor Bos
    Toju Duke
    Tulsee Doshi
    Vincent Y. Zhao
    Will Rusch
    Yuanzhong Xu
    arXiv (2022)
    Preview abstract We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and arepre-trained on 1.56T words of public dialog data and web text. While model scaling alone canimprove quality, it shows less improvements on safety and factual grounding. We demonstrate thatfine-tuning with annotated data and enabling the model to consult external knowledge sources canlead to significant improvements towards the two key challenges of safety and factual grounding.The first challenge, safety, involves ensuring that the model’s responses are consistent with a set ofhuman values, such as preventing harmful suggestions and unfair bias. We quantify safety using ametric based on an illustrative set of values, and we find that filtering candidate responses using aLaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promisingapproach to improving model safety. The second challenge, factual grounding, involves enabling themodel to consult external knowledge sources, such as an information retrieval system, a languagetranslator, and a calculator. We quantify factuality using a groundedness metric, and we find that ourapproach enables the model to generate responses grounded in known sources, rather than responsesthat merely sound plausible. Finally, we explore the use of LaMDA in the domains of education andcontent recommendations, and analyze their helpfulness and role consistency. View details
    Preview abstract In this paper we share findings from our effort towards building practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results across three research domains: (i) Building clean, web-mined datasets by leveraging semi-supervised pre-training for language-id and developing data-driven filtering techniques; (ii) Leveraging massively multilingual MT models trained with supervised parallel data for over $100$ languages and small monolingual datasets for over $1000$ languages to enable translation for several previously under-studied languages; and (iii) Studying the limitations of evaluation metrics for long tail languages and conducting qualitative analysis of the outputs from our MT models. We hope that our work provides useful insights to practitioners working towards building MT systems for long tail languages, and highlights research directions that can complement the weaknesses of massively multilingual pre-trained models in data-sparse settings. View details
    Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning
    Danyang Zhuo
    Hao Zhang
    Ion Stoica
    Joseph E. Gonzalez
    Lianmin Zheng
    Yida Wang
    Yonghao Zhuang
    Yuanzhong Xu
    Zhuohan Li
    16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), USENIX Association (2022), pp. 559-578
    Preview abstract Alpa automates model-parallel training of large deep learning (DL) models by generating execution plans that unify data, operator, and pipeline parallelism. Existing model-parallel training systems either require users to manually create a parallelization plan or automatically generate one from a limited space of model parallelism configurations. They do not suffice to scale out complex DL models on distributed compute devices. Alpa distributes the training of large DL models by viewing parallelisms as two hierarchical levels: inter-operator and intra-operator parallelisms. Based on it, Alpa constructs a new hierarchical space for massive model-parallel execution plans. Alpa designs a number of compilation passes to automatically derive efficient parallel execution plans at each parallelism level. Alpa implements an efficient runtime to orchestrate the two-level parallel execution on distributed compute devices. Our evaluation shows Alpa generates parallelization plans that match or outperform hand-tuned model-parallel training systems even on models they are designed for. Unlike specialized systems, Alpa also generalizes to models with heterogeneous architectures and models without manually-designed plans. Alpa's source code is publicly available at https://github.com/alpa-projects/alpa View details
    A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
    Yanzhang (Ryan) He
    Bo Li
    Ruoming Pang
    Antoine Bruguier
    Wei Li
    Raziel Alvarez
    Chung-Cheng Chiu
    David Garcia
    Kevin Hu
    Minho Jin
    Qiao Liang
    (June) Yuan Shangguan
    Yash Sheth
    Mirkó Visontai
    Yu Zhang
    Ding Zhao
    ICASSP (2020)
    Preview abstract Thus far, end-to-end (E2E) models have not shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer that surpasses a conventional model in both quality and latency. On the quality side, we incorporate a large number of utterances across varied domains to increase acoustic diversity and the vocabulary seen by the model. We also train with accented English speech to make the model more robust to different pronunciations. In addition, given the increased amount of training data, we explore a varied learning rate schedule. On the latency front, we explore using the end-of-sentence decision emitted by the RNN-T model to close the microphone, and also introduce various optimizations to improve the speed of LAS rescoring. Overall, we find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model. For example, for the same latency, RNN-T+LAS obtains a 8% relative improvement in WER, while being more than 400-times smaller in model size. View details
    GShard: Scaling Giant Models With Conditional Computation and Automatic Sharding
    Dehao Chen
    Dmitry (Dima) Lepikhin
    HyoukJoong Lee
    Maxim Krikun
    Noam Shazeer
    Yuanzhong Xu
    ICLR 2021 (2020) (to appear)
    Preview abstract Neural network scaling has been critical for improving the model quality in many real world machine learning applications with vast amounts of training data and compute. Although this trend of scaling is affirmed to be a sure-fire approach for better model quality, there are challenges on the path such as the computation cost, ease of programming, and efficient implementation on parallel devices. GShard is a module composed of a set of lightweight annotation APIs and an extension to the XLA compiler. It provides an elegant way to express a wide range of parallel computation patterns with minimal changes of existing model code. It enabled us to scale up multilingual machine translation Transformer model with Sparsely-Gated Mixture-of-Experts beyond 600 billion parameters using automatic sharding. We demonstrate that such a giant model can be easily trained on 2048 TPU v3 accelerators in 4 days to achieve far superior quality for translation from 100 languages to English compared to the prior art. View details
    Preview abstract This paper introduces a new speech corpus called ``LibriTTS'' designed for text-to-speech use. It is derived from the original audio and text materials of the LibriSpeech corpus, which has been used for training and evaluating automatic speech recognition systems. The new corpus inherits desired properties of the LibriSpeech corpus while addressing a number of issues which make LibriSpeech less than ideal for text-to-speech work. The released corpus consists of 585 hours of speech data at 24kHz sampling rate from 2,456 speakers and the corresponding texts. Experimental results show that neural end-to-end TTS models trained from the LibriTTS corpus achieved above 4.0 in mean opinion scores in naturalness in five out of six evaluation speakers. The corpus is freely available for download from http://www.openslr.org/60/. View details
    Preview abstract We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across languages, e.g. synthesize fluent Spanish speech using an English speaker's voice, without training on any bilingual or parallel examples. Such transfer works across distantly related languages, e.g. English and Mandarin. Critical to achieving this result are: 1. using a phonemic input representation to encourage sharing of model capacity across languages, and 2. incorporating an adversarial loss term to encourage the model to disentangle its representation of speaker identity (which is perfectly correlated with language in the training data) from the speech content. Further scaling up the model by training on multiple speakers of each language, and incorporating an autoencoding input to help stabilize attention during training, results in a model which can be used to consistently synthesize intelligible speech for training speakers in all languages seen during training, and in native or foreign accents. View details
    Preview abstract We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that are crucial to the quality and practicality towards universal NMT. While we prototype a high-quality universal translation system, our extensive empirical analysis exposes issues that need to be further addressed, and we suggest directions for future research. View details
    Zanzibar: Google’s Consistent, Global Authorization System
    Ruoming Pang
    Ramon Caceres
    Mike Burrows
    Pratik Dave
    Alexander Golynski
    Nina Kang
    Lea Kissner
    Abhishek Parmar
    Christina D. Richards
    Mengzhi Wang
    2019 USENIX Annual Technical Conference (USENIX ATC '19), Renton, WA
    Preview abstract Determining whether online users are authorized to access digital objects is central to preserving privacy. This paper presents the design, implementation, and deployment of Zanzibar, a global system for storing and evaluating access control lists. Zanzibar provides a uniform data model and configuration language for expressing a wide range of access control policies from hundreds of client services at Google, including Calendar, Cloud, Drive, Maps, Photos, and YouTube. Its authorization decisions respect causal ordering of user actions and thus provide external consistency amid changes to access control lists and object contents. Zanzibar scales to trillions of access control lists and millions of authorization requests per second to support services used by billions of people. It has maintained 95th-percentile latency of less than 10 milliseconds and availability of greater than 99.999% over 3 years of production use. View details
    Preview abstract Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks. In many cases, increasing model capacity beyond the memory limit of a single accelerator has required developing special algorithms or infrastructure. These solutions are often architecture-specific and do not transfer to other tasks. To address the need for efficient and task-independent model parallelism, we introduce GPipe, a pipeline parallelism library that allows scaling any network that can be expressed as a sequence of layers. By pipelining different sub-sequences of layers on separate accelerators, GPipe provides the flexibility of scaling a variety of different networks to gigantic sizes efficiently. Moreover, GPipe utilizes a novel batch-splitting pipelining algorithm, resulting in almost linear speedup when a model is partitioned across multiple accelerators. We demonstrate the advantages of GPipe by training large-scale neural networks on two different tasks with distinct network architectures: (i) Image Classification: We train a 557-million-parameter AmoebaNet model and attain a top-1 accuracy of 84.4% on ImageNet-2012, (ii) Multilingual Neural Machine Translation: We train a single 6-billion-parameter, 128-layer Transformer model on a corpus spanning over 100 languages and achieve better quality than all bilingual models. View details
    Preview abstract In this paper, we present Smart Compose, a novel system for generating interactive, real-time suggestions in Gmail that assists users in writing mails by reducing repetitive typing. In the design and deployment of such a large-scale and complicated system, we faced several challenges including model selection, performance evaluation, serving and other practical issues. At the core of Smart Compose is a large-scale neural language model. We leveraged state-of-the-art machine learning techniques for language model training which enabled high-quality suggestion prediction, and constructed novel serving infrastructure for high-throughput and real-time inference. Experimental results show the effectiveness of our proposed system design and deployment approach. This system is currently being served in Gmail. View details
    Preview abstract We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a different canonical voice). We further demonstrate the ability to synthesize translated speech using the voice of the source speaker. We conduct experiments on two Spanish-to-English speech translation datasets, and find that the proposed model slightly underperforms a baseline cascade of a direct speech-to-text translation model and a text-to-speech synthesis model, demonstrating the feasibility of the approach on this very challenging task. View details
    Hierarchical Generative Modeling for Controllable Speech Synthesis
    Wei-Ning Hsu
    Yu Zhang
    Yuxuan Wang
    Yuan Cao
    Ye Jia
    Jonathan Shen
    Patrick Nguyen
    Ruoming Pang
    International Conference on Learning Representations (2019)
    Preview abstract This paper proposes a neural end-to-end text-to-speech model which can control latent attributes in the generation of speech, that are rarely annotated in the training data (e.g. speaking styles, accents, background noise level, and recording conditions). The model is formulated as a conditional generative model with two levels of hierarchical latent variables. The first level is a categorical variable, which represents attribute groups (e.g. clean/noisy) and provides interpretability. The second level, conditioned on the first, is a multivariate Gaussian variable, which characterizes specific attribute configurations (e.g. noise level, speaking rate) and enables disentangled fine-grained control over these attributes. This amounts to using a Gaussian mixture model (GMM) for the latent distribution. Extensive evaluation of the proposed model demonstrates its ability to control the aforementioned attributes. In particular, it is capable of consistently synthesizing high-quality clean speech regardless of the quality of the training data for the target speaker. View details
    Preview abstract Multilingual end-to-end (E2E) models have shown great promise as a means to expand coverage of the world’s lan- guages by automatic speech recognition systems. They im- prove over monolingual E2E systems, especially on low re- source languages, and simplify training and serving by elimi- nating language-specific acoustic, pronunciation, and language models. This work aims to develop an E2E multilingual system which is equipped to operate in low-latency interactive applica- tions as well as handle the challenges of real world imbalanced data. First, we present a streaming E2E multilingual model. Second, we compare techniques to deal with imbalance across languages. We find that a combination of conditioning on a language vector and training language-specific adapter layers produces the best model. The resulting E2E multilingual model system achieves lower word error rate (WER) than state-of-the- art conventional monolingual models by at least 10% relative on every language. View details
    Natural TTS Synthesis By Conditioning WaveNet On Mel Spectrogram Predictions
    Jonathan Shen
    Ruoming Pang
    Mike Schuster
    Navdeep Jaitly
    Zongheng Yang
    Yu Zhang
    Yuxuan Wang
    Yannis Agiomyrgiannakis
    ICASSP (2018)
    Preview abstract This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and F0 features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture. View details
    Preview abstract Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system performance is usually measured in terms of word error rate (WER), not log-likelihood. Traditional ASR systems benefit from discriminative sequence training which optimizes criteria such as the state-level minimum Bayes risk (sMBR) which are more closely related to WER. In the present work, we explore techniques to train attention-based models to directly minimize expected word error rate. We consider two loss functions which approximate the expected number of word errors: either by sampling from the model, or by using N-best lists of decoded hypotheses, which we find to be more effective than the sampling-based method. In experimental evaluations, we find that the proposed training procedure improves performance by up to 8.2% relative to the baseline system. This allows us to train grapheme-based, uni-directional attention-based models which match the performance of a traditional, state-of-the-art, discriminative sequence-trained system on a mobile voice-search task. View details
    Preview abstract Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network. In our previous work, we have shown that such architectures are comparable to state-of-the-art ASR systems on dictation tasks, but it was not clear if such architectures would be practical for more challenging tasks such as voice search. In this work, we explore a variety of structural and optimization improvements to our LAS model which significantly improve performance. On the structural side, we show that word piece models can be used instead of graphemes. We introduce a multi-head attention architecture, which offers improvements over the commonly-used single-head attention. On the optimization side, we explore techniques such as synchronous training, scheduled sampling, label smoothing, and minimum word error rate optimization, which are all shown to improve accuracy. We present results with a unidirectional LSTM encoder for streaming recognition. On a 12,500 hour voice search task, we find that the proposed changes improve the WER of the LAS system from 9.2% to 5.6%, while the best conventional system achieve 6.7% WER. We also test both models on a dictation dataset, and our model provide 4.1% WER while the conventional system provides 5% WER. View details
    Preview abstract Having an sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown to degrade significantly in performance compared to non-streaming models such as Listen, Attend and Spell (LAS). In this paper, we present various improvements to NT. Specifically, we look at increasing the window over which NT computes attention, mainly by looking backwards in time so the model still remains online. In addition, we explore initializing a NT model from a LAS-trained model so that it is guided with a better alignment. Finally. we explore including stronger language models such as using wordpiece models, and applying an external LM during the beam search. On a Voice Search task, we find with these improvements we can get NT to match the performance of LAS. View details
    Preview abstract The past year has witnessed rapid advances in sequence-to-sequence (seq2seq) modeling for Machine Translation (MT). The classic RNN-based approaches to MT were first out-performed by the convolutional seq2seq model, which was then out-performed by the more recent Transformer model. Each of these new approaches consists of a fundamental architecture accompanied by a set of modeling and training techniques that are in principle applicable to other seq2seq architectures. In this paper, we tease apart the new architectures and their accompanying techniques in two ways. First, we identify several key modeling and training techniques, and apply them to the RNN architecture, yielding a new RNMT+ model that outperforms all of the three fundamental architectures on the benchmark WMT'14 English to French and English to German tasks. Second, we analyze the properties of each fundamental seq2seq architecture and devise new hybrid architectures intended to combine their strengths. Our hybrid models obtain further improvements, outperforming the RNMT+ model on both benchmark datasets. View details
    Preview abstract We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation. View details
    Preview abstract For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which typically predict graphemes or words, simplify the recognition process since they remove the need for a separate expert-curated pronunciation lexicon to map from phoneme-based units to words. However, there has been little previous work comparing phoneme-based versus grapheme-based sub-word units in the end-to-end modeling framework, to determine whether the gains from such approaches are primarily due to the new probabilistic model, or from the joint learning of the various components with grapheme-based units. In this work, we conduct detailed experiments which are aimed at quantifying the value of phoneme-based pronunciation lexica in the context of end-to-end models. We examine phoneme-based end-to-end models, which are contrasted against grapheme-based ones on a large vocabulary English Voice-search task, where we find that graphemes do indeed outperform phoneme-based models. We also compare grapheme and phoneme-based end-to-end approaches on a multi-dialect English task, which once again confirm the superiority of graphemes, greatly simplifying the system for recognizing multiple dialects. View details
    Preview abstract Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This leads to the use of shallow fusion with an external language model at inference time. Shallow fusion refers to log-linear interpolation with a separately trained language model at each step of the beam search. In this work, we investigate the behavior of shallow fusion across a range of conditions: different types of language models, different decoding units, and different tasks. On Google Voice Search, we demonstrate that the use of shallow fusion with an neural LM with wordpieces yields a 9.1% relative word error rate reduction (WERR) over our competitive attention-based sequence-to-sequence model, obviating the need for second-pass rescoring. View details
    Preview abstract A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given (text, audio) pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods. View details
    Preview abstract We present a recurrent encoder-decoder deep neural network architecture that directly translates speech in one language into text in another. The model does not explicitly transcribe the speech into text in the source language, nor does it require supervision from the ground truth source language transcription during training. We apply a slightly modified sequence-to-sequence with attention architecture that has previously been used for speech recognition and show that it can be repurposed for this more complex task, illustrating the power of attention-based models. A single model trained end-to-end obtains state-of-the-art performance on the Fisher Callhome Spanish-English speech translation task, outperforming a cascade of independently trained sequence-to-sequence speech recognition and machine translation models by 1.8 BLEU points on the Fisher test set. In addition, we find that making use of the training data in both languages by multi-task training sequence-to-sequence speech translation and recognition models with a shared encoder network can improve performance by a further 1.4 BLEU points. View details
    Reward Augmented Maximum Likelihood for Neural Structured Prediction
    Mohammad Norouzi
    Samy Bengio
    Navdeep Jaitly
    Mike Schuster
    Dale Schuurmans
    NIPS (2016)
    Preview abstract A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally efficient approach to incorporate task reward into a maximum likelihood framework. We establish a connection between the log-likelihood and regularized expected reward objectives, showing that at a zero temperature, they are approximately equivalent in the vicinity of the optimal solution. We show that optimal regularized expected reward is achieved when the conditional distribution of the outputs given the inputs is proportional to their exponentiated (temperature adjusted) rewards. Based on this observation, we optimize conditional log-probability of edited outputs that are sampled proportionally to their scaled exponentiated reward. We apply this framework to optimize edit distance in the output label space. Experiments on speech recognition and machine translation for neural sequence to sequence models show notable improvements over a maximum likelihood baseline by using edit distance augmented maximum likelihood. View details
    TensorFlow: A system for large-scale machine learning
    Jianmin Chen
    Matthieu Devin
    Geoffrey Irving
    Manjunath Kudlur
    Rajat Monga
    Benoit Steiner
    Paul Tucker
    Vijay Vasudevan
    Pete Warden
    Yuan Yu
    Xiaoqiang Zheng
    12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), USENIX Association (2016), pp. 265-283
    Preview abstract TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. TensorFlow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of a dataflow graph across many machines in a cluster, and within a machine across multiple computational devices, including multicore CPUs, general-purpose GPUs, and custom-designed ASICs known as Tensor Processing Units (TPUs). This architecture gives flexibility to the application developer: whereas in previous “parameter server” designs the management of shared state is built into the system, TensorFlow enables developers to experiment with novel optimizations and training algorithms. TensorFlow supports a variety of applications, with a focus on training and inference on deep neural networks. Several Google services use TensorFlow in production, we have released it as an open-source project, and it has become widely used for machine learning research. In this paper, we describe the TensorFlow dataflow model and demonstrate the compelling performance that Tensor- Flow achieves for several real-world applications. View details
    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
    Mike Schuster
    Mohammad Norouzi
    Maxim Krikun
    Yuan Cao
    Qin Gao
    Apurva Shah
    Xiaobing Liu
    Łukasz Kaiser
    Stephan Gouws
    Taku Kudo
    Keith Stevens
    George Kurian
    Nishant Patil
    Wei Wang
    Cliff Young
    Jason Smith
    Alex Rudnick
    Macduff Hughes
    CoRR, vol. abs/1609.08144 (2016)
    Preview abstract Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference. Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using attention and residual connections. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system. View details
    Preview abstract We propose a simple, elegant solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no change in the model architecture from our base system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. The rest of the model, which includes encoder, decoder and attention, remains unchanged and is shared across all languages. Using a shared wordpiece vocabulary, our approach enables Multilingual NMT using a single model without any increase in parameters, which is significantly simpler than previous proposals for Multilingual NMT. Our method often improves the translation quality of all involved language pairs, even while keeping the total number of model parameters constant. On the WMT'14 benchmarks, a single multilingual model achieves comparable performance for English->French and surpasses state-of-the-art results for English->German. Similarly, a single multilingual model surpasses state-of-the-art results for French->English and German->English on WMT'14 and WMT'15 benchmarks respectively. On production corpora, multilingual models of up to twelve language pairs allow for better translation of many individual pairs. In addition to improving the translation quality of language pairs that the model was trained with, our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation. Finally, we show analyses that hints at a universal interlingua representation in our models and show some interesting examples when mixing languages. View details
    TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
    Ashish Agarwal
    Eugene Brevdo
    Craig Citro
    Matthieu Devin
    Ian Goodfellow
    Andrew Harp
    Geoffrey Irving
    Yangqing Jia
    Rafal Jozefowicz
    Lukasz Kaiser
    Manjunath Kudlur
    Dan Mané
    Rajat Monga
    Chris Olah
    Mike Schuster
    Jonathon Shlens
    Benoit Steiner
    Ilya Sutskever
    Kunal Talwar
    Paul Tucker
    Vijay Vasudevan
    Pete Warden
    Yuan Yu
    Xiaoqiang Zheng
    tensorflow.org (2015)
    Preview abstract TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous systems, ranging from mobile devices such as phones and tablets up to large-scale distributed systems of hundreds of machines and thousands of computational devices such as GPU cards. The system is flexible and can be used to express a wide variety of algorithms, including training and inference algorithms for deep neural network models, and it has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields, including speech recognition, computer vision, robotics, information retrieval, natural language processing, geographic information extraction, and computational drug discovery. This paper describes the TensorFlow interface and an implementation of that interface that we have built at Google. The TensorFlow API and a reference implementation were released as an open-source package under the Apache 2.0 license in November, 2015 and are available at www.tensorflow.org. View details
    Fast and memory-efficient regular expression matching for deep packet inspection
    Fang Yu
    Yanlei Diao
    T. V. Lakshman
    Randy H. Katz
    Proc. 2006 ACM/IEEE Symposium on Architecture for networking and communication systems, ACM, San Jose, CA, pp. 93-102
    Preview
    Hibernator: helping disk arrays sleep through the winter
    Qingbo Zhu
    Lin Tan
    Yuanyuan Zhou
    Kimberly Keeton
    SOSP (2005), pp. 177-190