Speech Processing

The research goal for speech at Google aligns with our company mission: to organize the world’s information and make it universally accessible and useful. Our pioneering research work in speech processing has enabled us to build automatic speech recognition (ASR) and text-to-speech (TTS) systems that are used across Google products, with support for more than a hundred language varieties spoken across the globe. From Gboard dictation to transcriptions of voice notes, from YouTube captions to team meetings without language barriers, and from Google Maps speaking directions aloud to Google Assistant reading the news, Google’s speech research has unparalleled reach and impact. We aim to solve speech for everyone, everywhere – and work to further improve quality, speed and versatility across all kinds of speech. We're also committed to expanding our language coverage, and have set a moonshot goal to build speech technologies for 1,000 languages.

Google's speech research efforts push the state-of-the-art on architectures and algorithms used across areas like speech recognition, text-to-speech synthesis, keyword spotting, speaker recognition, and language identification. The systems we build are deployed on servers in Google’s data centers but also increasingly on-device. The team has a passion for research that leads to product advances for the billions of users that use speech in Google products today. We also release academic publications and open-source projects for the broader research community to leverage.

Our speech technologies are embedded in products like the Assistant, Search, Gboard, Translate, Maps, YouTube, Cloud, and many more. Thanks to close collaborations with product teams, we are in a unique position to deliver user-centric research. Our researchers can conduct live experiments to test and benchmark new algorithms directly in a realistic controlled environment. Whether these are algorithmic improvements or user experience and human-computer interaction studies, we focus on solving real problems with real impact on users.

We value our user diversity, and have made it a priority to deliver the best performance to every language and language variety. Today, our speech systems operate in more than 130 language varieties, and we continue to expand our reach. The challenges of internationalizing at scale are immense and rewarding. We are breaking new ground by deploying speech technologies that help people communicate, access information online, and share their knowledge – all in their language. And combined with the unprecedented translation capabilities of Google Translate, we are also at the forefront of research in speech-to-speech translation and one step closer to a universal translator.

Recent Publications

Preview abstract This paper presents NOMAD (Non-Matching Audio Distance), a differentiable perceptual similarity metric that measures the distance of a degraded signal against non-matching references. The proposed method is based on learning deep feature embeddings via a triplet loss guided by the Neurogram Similarity Index Measure (NSIM) to capture degradation intensity. During inference, the similarity score between any two audio samples is computed through Euclidean distance of their embeddings. NOMAD is fully unsupervised and can be used in general perceptual audio tasks for audio analysis e.g. quality assessment and generative tasks such as speech enhancement and speech synthesis. The proposed method is evaluated with 3 tasks. Ranking degradation intensity, predicting speech quality, and as a loss function for speech enhancement. Results indicate NOMAD outperforms other non-matching reference approaches in both ranking degradation intensity and quality assessment, exhibiting competitive performance with full-reference audio metrics. NOMAD demonstrates a promising technique that mimics human capabilities in assessing audio quality with non-matching references to learn perceptual embeddings without the need for human-generated labels. View details
Automatic Speech Recognition of Conversational Speech in Individuals with Disordered Speech
Bob MacDonald
Rus Heywood
Richard Cave
Katie Seaver
Antoine Desjardins
Jordan Green
Journal of Speech, Language, and Hearing Research(2024) (to appear)
Preview abstract Purpose: This study examines the effectiveness of automatic speech recognition (ASR) for individuals with speech disorders, addressing the gap in performance between read and conversational ASR. We analyze the factors influencing this disparity and the effect of speech mode-specific training on ASR accuracy. Method: Recordings of read and conversational speech from 27 individuals with various speech disorders were analyzed using both (1) one speaker-independent ASR system trained and optimized for typical speech and (2) multiple ASR models that were personalized to the speech of the participants with disordered speech. Word Error Rates (WERs) were calculated for each speech mode, read vs conversational, and subject. Linear mixed-effect models were used to assess the impact of speech mode and disorder severity on ASR accuracy. We investigated nine variables, classified as technical, linguistic, or speech impairment factors, for their potential influence on the performance gap. Results: We found a significant performance gap between read and conversational speech in both personalized and unadapted ASR models. Speech impairment severity notably impacted recognition accuracy in unadapted models for both speech modes and in personalized models for read speech. Linguistic attributes of utterances were the most influential on accuracy, though atypical speech characteristics also played a role. Including conversational speech samples in model training notably improved recognition accuracy. Conclusions: We observed a significant performance gap in ASR accuracy between read and conversational speech for individuals with speech disorders. This gap was largely due to the linguistic complexity and unique characteristics of speech disorders in conversational speech. Training personalized ASR models using conversational speech significantly improved recognition accuracy, demonstrating the importance of domain-specific training and highlighting the need for further research into ASR systems capable of handling disordered conversational speech effectively. View details
Preview abstract We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech. Unlike previous approaches, StreamVC produces the resulting waveform at low latency from the input signal even on a mobile platform, making it applicable to real-time communication scenarios like calls and video conferencing, and addressing use cases such as voice anonymization in these scenarios. Our design leverages the architecture and training strategy of the SoundStream neural audio codec for lightweight high-quality speech synthesis. We demonstrate the feasibility of learning soft speech units causally, as well as the effectiveness of supplying whitened fundamental frequency information to improve pitch stability without leaking the source timbre information. View details
Preview abstract End-to-end models for speech recognition and speech synthesis have many benefits, but we argue they also face a unique set of challenges not encountered in conventional multi-stage hybrid systems, which relied on the explicit injection of linguistic knowledge through resources such as phonemic dictionaries and verbalization grammars. These challenges include handling words with unusual grapheme-to-phoneme correspondences, converting between written forms like ‘12’ and spoken forms such as ‘twelve’, and contextual disambiguation of homophones or homographs. We describe the mitigation strategies that have been used for these problems in end-to-end systems, either implicitly or explicitly, and call out that the most commonly used mitigation techniques are likely incompatible with newly emerging approaches that use minimal amounts of supervised audio training data. We review best-of-both-world approaches that allow the use of end-to-end models combined with traditional linguistic resources, which we show are increasingly straightforward to create at scale, and close with an optimistic outlook for bringing speech technologies to many more languages by combining these strands of research. View details
USM-SCD: USM-Based Multilingual Speaker Change Detection
Yongqiang Wang
Jason Pelecanos
Yu Zhang
Yiling Huang
Han Lu
ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11801-11805
Preview abstract We introduce a multilingual speaker change detection model (USM- SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model is adapted from a speech foundation model trained on a large quantity of supervised and unsupervised data, demonstrating the utility of fine-tuning from a large generic foundation model for a downstream task. We analyze the performance of this multilingual speaker change detection model through a series of ablation studies. We show that the USM-SCD model can achieve more than 75% average speaker change detection F1 score across a test set that consists of data from 96 languages. On American English, the USM-SCD model can achieve an 85.8% speaker change detection F1 score across various public and internal test sets, beating the previous monolingual baseline model by 21% relative. We also show that we only need to fine-tune one-quarter of the trainable model parameters to achieve the best model performance. The USM-SCD model exhibits state-of-the-art ASR quality compared with a strong public ASR baseline, making it suitable to handle both tasks with negligible additional computational cost. View details
Preview abstract We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. By endowing the LLM with a pre-trained speech encoder, our model becomes able to take speech inputs and generate speech outputs. The entire system is trained endto-end and operates directly on spectrograms, simplifying our architecture. Key to our approach is a training objective that jointly supervises speech recognition, text continuation, and speech synthesis using only paired speech-text pairs, enabling a ‘cross-modal’ chain-of-thought within a single decoding pass. Our method surpasses existing spoken language models in speaker preservation and semantic coherence. Furthermore, the proposed model improves upon direct initialization in retaining the knowledge of the original LLM as demonstrated through spoken QA datasets. We release our audio samples and spoken QA dataset via our website. View details