Yuma Koizumi
Yuma Koizumi is a research scientist at Google Research. He received his B.S. and M.S degrees in 2012 and 2014 from Hosei University, Tokyo, respectively, and his Ph.D. degree in 2017 from the University of Electro-Communications, Tokyo. He was with the NTT Media Intelligence Laboratories at Nippon Telegraph and Telephone (NTT), Tokyo between 2014 and 2020. His current research interests are speech enhancement, environmental sound analysis, and automatic speech recognition.
Research Areas
Authored Publications
Sort By
Google
Description and Discussion on DCASE 2023 Challenge Task 2: First-shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring
Kota Dohi
Keisuke Imoto
Noboru Harada
Daisuke Niizumi
Tomoya Nishida
Harsh Purohit
Ryo Tanabe
Takashi Endo
Yohei Kawaguchi
DCASE 2023 (2023) (to appear)
Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech Representation and Linguistic Features
Yifan Ding
Kohei Yatabe
Nobuyuki Morioka
Yu Zhang
Wei Han
WASPAA 2023 (2023) (to appear)
LibriTTS-R: Restoration of a Large-Scale Multi-Speaker TTS Corpus
Yifan Ding
Kohei Yatabe
Nobuyuki Morioka
Yu Zhang
Wei Han
Interspeech 2023 (2023)
Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques
Kota Dohi
Keisuke Imoto
Noboru Harada
Daisuke Niizumi
Tomoya Nishida
Harsh Purohit
Takashi Endo
Masaaki Yamamoto
Yohei Kawaguchi
DCASE 2022 Workshop (2022)
WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
Kohei Yatabe
Proc. IEEE Spoken Language Technology Workshop (SLT) (2022) (to appear)
SNRi Target Training for Joint Speech Enhancement and Recognition
Sankaran Panchapagesan
Proc. Interspeech (2022) (to appear)
SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping
Kohei Yatabe
Nanxin Chen
Proc. Interspeech (2022) (to appear)
DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement
Lion Jones
Proc. IEEE Workshop Appl. Signal Process. Audio Acoust. (WASPAA) (2021)
Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions
Yohei Kawaguchi
Keisuke Imoto
Noboru Harada
Daisuke Niizumi
Kota Dohi
Ryo Tanabe
Harsh Purohit
Takashi Endo
Proceedings of Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE) (2021) (to appear)
