Michiel Bacchiani

91 papers A* 1A 24C 2Misc 19Journal 24Unranked 19

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration. WASPAA Shigeki Karita, Yuma Koizumi, Heiga Zen, Haruko Ishikawa, Robin Scheibler, Michiel Bacchiani
2025	J	`jnl`	Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration. CoRR Shigeki Karita, Yuma Koizumi, Heiga Zen, Haruko Ishikawa, Robin Scheibler, Michiel Bacchiani
2025	—	`conf`	ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability. WASPAA Wataru Nakata, Yuma Koizumi, Shigeki Karita, Robin Scheibler, Haruko Ishikawa, Adriana Guevara-Rukoz, Heiga Zen, Michiel Bacchiani
2025	J	`jnl`	ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability. CoRR Wataru Nakata, Yuma Koizumi, Shigeki Karita, Robin Scheibler, Haruko Ishikawa, Adriana Guevara-Rukoz, Heiga Zen, Michiel Bacchiani
2024	J	`jnl`	Adaptive Dropout for Pruning Conformers. CoRR Yotaro Kubo, Xingyu Cai, Michiel Bacchiani
2024	A	`conf`	FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks. INTERSPEECH Min Ma, Yuma Koizumi, Shigeki Karita, Heiga Zen, Jason Riesa, Haruko Ishikawa, Michiel Bacchiani
2024	J	`jnl`	FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks. CoRR Min Ma, Yuma Koizumi, Shigeki Karita, Heiga Zen, Jason Riesa, Haruko Ishikawa, Michiel Bacchiani
2023	A	`conf`	LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus. INTERSPEECH Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, Ankur Bapna
2023	J	`jnl`	LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus. CoRR Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Michiel Bacchiani, Yu Zhang, Wei Han, Ankur Bapna
2023	—	`conf`	Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations. WASPAA Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Yu Zhang, Wei Han, Ankur Bapna, Michiel Bacchiani
2023	J	`jnl`	Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations. CoRR Yuma Koizumi, Heiga Zen, Shigeki Karita, Yifan Ding, Kohei Yatabe, Nobuyuki Morioka, Yu Zhang, Wei Han, Ankur Bapna, Michiel Bacchiani
2022	Misc	`conf`	Knowledge Transfer from Large-Scale Pretrained Language Models to End-To-End Speech Recognizers. ICASSP Yotaro Kubo, Shigeki Karita, Michiel Bacchiani
2022	J	`jnl`	Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers. CoRR Yotaro Kubo, Shigeki Karita, Michiel Bacchiani
2022	A	`conf`	SNRi Target Training for Joint Speech Enhancement and Recognition. INTERSPEECH Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani
2022	A	`conf`	SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping. INTERSPEECH Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani
2022	J	`jnl`	SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping. CoRR Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani
2022	J	`jnl`	WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration. CoRR Yuma Koizumi, Kohei Yatabe, Heiga Zen, Michiel Bacchiani
2022	—	`conf`	Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration. SLT Yuma Koizumi, Kohei Yatabe, Heiga Zen, Michiel Bacchiani
2021	—	`conf`	DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement. WASPAA Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
2021	J	`jnl`	DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement. CoRR Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
2021	J	`jnl`	SNRi Target Training for Joint Speech Enhancement and Recognition. CoRR Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani
2020	Misc	`conf`	Joint Phoneme-Grapheme Model for End-To-End Speech Recognition. ICASSP Yotaro Kubo, Michiel Bacchiani
2019	J	`jnl`	Introduction to the Issue on Far-Field Speech Processing in the Era of Deep Learning: Speech Enhancement, Separation, and Recognition. IEEE J. Sel. Top. Signal Process. Shinji Watanabe, Shoko Araki, Michiel Bacchiani, Reinhold Haeb-Umbach, Michael L. Seltzer
2019	J	`jnl`	Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling. CoRR Jonathan Shen, Patrick Nguyen, Yonghui Wu, Zhifeng Chen, Mia Xu Chen, Ye Jia, Anjuli Kannan, Tara N. Sainath, Yuan Cao, Chung-Cheng Chiu, Yanzhang He, Jan Chorowski, Smit Hinsu, Stella Laurenzo, James Qin, Orhan Firat, Wolfgang Macherey, Suyog Gupta, Ankur Bapna, Shuyuan Zhang, Ruoming Pang, Ron J. Weiss, Rohit Prabhavalkar, Qiao Liang, Benoit Jacob, Bowen Liang, HyoukJoong Lee, Ciprian Chelba, Sébastien Jean, Bo Li, Melvin Johnson, Rohan Anil, Rajat Tibrewal, Xiaobing Liu, Akiko Eriguchi, Navdeep Jaitly, Naveen Ari, Colin Cherry, Parisa Haghani, Otavio Good, Youlong Cheng, Raziel Alvarez, Isaac Caswell, Wei-Ning Hsu, Zongheng Yang, Kuan-Chieh Wang, Ekaterina Gonina, Katrin Tomanek, Ben Vanik, Zelin Wu, Llion Jones, Mike Schuster, Yanping Huang, Dehao Chen, Kazuki Irie, George F. Foster, John Richardson, Klaus Macherey, Antoine Bruguier, Heiga Zen, Colin Raffel, Shankar Kumar, Kanishka Rao, David Rybach, Matthew Murray, Vijayaditya Peddinti, Maxim Krikun, Michiel Bacchiani, Thomas B. Jablin, Robert Suderman, Ian Williams, Benjamin Lee, Deepti Bhatia, Justin Carlson, Semih Yavuz, Yu Zhang, Ian McGraw, Max Galkin, Qi Ge, Golan Pundak, Chad Whipkey, Todd Wang, Uri Alon, Dmitry Lepikhin, Ye Tian, Sara Sabour, William Chan, Shubham Toshniwal, Baohua Liao, Michael Nirschl, Pat Rondon
2019	J	`jnl`	Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques. IEEE Signal Process. Mag. Reinhold Haeb-Umbach, Shinji Watanabe, Tomohiro Nakatani, Michiel Bacchiani, Björn Hoffmeister, Michael L. Seltzer, Heiga Zen, Mehrez Souden
2018	J	`jnl`	An Overview of the IEEE SPS Speech and Language Technical Committee [In the Spotlight]. IEEE Signal Process. Mag. Michiel Bacchiani, Eric Fosler-Lussier
2018	A	`conf`	Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition. INTERSPEECH Khe Chai Sim, Arun Narayanan, Ananya Misra, Anshuman Tripathi, Golan Pundak, Tara N. Sainath, Parisa Haghani, Bo Li, Michiel Bacchiani
2018	A	`conf`	Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models. INTERSPEECH Chanwoo Kim, Ehsan Variani, Arun Narayanan, Michiel Bacchiani
2018	—	`conf`	From Audio to Semantics: Approaches to End-to-End Spoken Language Understanding. SLT Parisa Haghani, Arun Narayanan, Michiel Bacchiani, Galen Chuang, Neeraj Gaur, Pedro J. Moreno, Rohit Prabhavalkar, Zhongdi Qu, Austin Waters
2018	J	`jnl`	From Audio to Semantics: Approaches to end-to-end spoken language understanding. CoRR Parisa Haghani, Arun Narayanan, Michiel Bacchiani, Galen Chuang, Neeraj Gaur, Pedro J. Moreno, Rohit Prabhavalkar, Zhongdi Qu, Austin Waters
2018	Misc	`conf`	Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model. ICASSP Bo Li, Tara N. Sainath, Khe Chai Sim, Michiel Bacchiani, Eugene Weinstein, Patrick Nguyen, Zhifeng Chen, Yanghui Wu, Kanishka Rao
2018	Misc	`conf`	Performance of Mask Based Statistical Beamforming in a Smart Home Scenario. ICASSP Jahn Heymann, Michiel Bacchiani, Tara N. Sainath
2018	Misc	`conf`	Sampled Connectionist Temporal Classification. ICASSP Ehsan Variani, Tom Bagby, Kamel Lahouel, Erik McDermott, Michiel Bacchiani
2018	Misc	`conf`	Sound Source Separation Using Phase Difference and Reliable Mask Selection Selection. ICASSP Chanwoo Kim, Anjali Menon, Michiel Bacchiani, Richard M. Stern
2018	Misc	`conf`	Spectral Distortion Model for Training Phase-Sensitive Deep-Neural Networks for Far-Field Speech Recognition. ICASSP Chanwoo Kim, Tara N. Sainath, Arun Narayanan, Ananya Misra, Rajeev C. Nongpiur, Michiel Bacchiani
2018	Misc	`conf`	State-of-the-Art Speech Recognition with Sequence-to-Sequence Models. ICASSP Chung-Cheng Chiu, Tara N. Sainath, Yonghui Wu, Rohit Prabhavalkar, Patrick Nguyen, Zhifeng Chen, Anjuli Kannan, Ron J. Weiss, Kanishka Rao, Ekaterina Gonina, Navdeep Jaitly, Bo Li, Jan Chorowski, Michiel Bacchiani
2018	—	`conf`	Toward Domain-Invariant Speech Recognition via Large Scale Training. SLT Arun Narayanan, Ananya Misra, Khe Chai Sim, Golan Pundak, Anshuman Tripathi, Mohamed Elfeky, Parisa Haghani, Trevor Strohman, Michiel Bacchiani
2018	J	`jnl`	Toward domain-invariant speech recognition via large scale training. CoRR Arun Narayanan, Ananya Misra, Khe Chai Sim, Golan Pundak, Anshuman Tripathi, Mohamed Elfeky, Parisa Haghani, Trevor Strohman, Michiel Bacchiani
2017	A	`conf`	Acoustic Modeling for Google Home. INTERSPEECH Bo Li, Tara N. Sainath, Arun Narayanan, Joe Caroselli, Michiel Bacchiani, Ananya Misra, Izhak Shafran, Hasim Sak, Golan Pundak, Kean K. Chin, Khe Chai Sim, Ron J. Weiss, Kevin W. Wilson, Ehsan Variani, Chanwoo Kim, Olivier Siohan, Mitchel Weintraub, Erik McDermott, Richard Rose, Matt Shannon
2017	J	`jnl`	Efficient Implementation of the Room Simulator for Training Deep Neural Network Acoustic Models. CoRR Chanwoo Kim, Ehsan Variani, Arun Narayanan, Michiel Bacchiani
2017	A	`conf`	End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow. INTERSPEECH Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani
2017	A	`conf`	Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home. INTERSPEECH Chanwoo Kim, Ananya Misra, Kean K. Chin, Thad Hughes, Arun Narayanan, Tara N. Sainath, Michiel Bacchiani
2017	C	`conf`	Improving the efficiency of forward-backward algorithm using batched computation in TensorFlow. ASRU Khe Chai Sim, Arun Narayanan, Tom Bagby, Tara N. Sainath, Michiel Bacchiani
2017	J	`jnl`	Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model. CoRR Bo Li, Tara N. Sainath, Khe Chai Sim, Michiel Bacchiani, Eugene Weinstein, Patrick Nguyen, Zhifeng Chen, Yonghui Wu, Kanishka Rao
2017	J	`jnl`	Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Bo Li, Arun Narayanan, Ehsan Variani, Michiel Bacchiani, Izhak Shafran, Andrew W. Senior, Kean K. Chin, Ananya Misra, Chanwoo Kim
2017	—	`ch.`	Raw Multichannel Processing Using Deep Neural Networks. New Era for Robust Speech Recognition, Exploiting Deep Learning Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Arun Narayanan, Michiel Bacchiani, Bo Li, Ehsan Variani, Izhak Shafran, Andrew W. Senior, Kean K. Chin, Ananya Misra, Chanwoo Kim
2017	—	`ch.`	Speech Research at Google to Enable Universal Speech Interfaces. New Era for Robust Speech Recognition, Exploiting Deep Learning Michiel Bacchiani, Françoise Beaufays, Alexander Gruenstein, Pedro J. Moreno, Johan Schalkwyk, Trevor Strohman, Heiga Zen
2017	J	`jnl`	State-of-the-art Speech Recognition With Sequence-to-Sequence Models. CoRR Chung-Cheng Chiu, Tara N. Sainath, Yonghui Wu, Rohit Prabhavalkar, Patrick Nguyen, Zhifeng Chen, Anjuli Kannan, Ron J. Weiss, Kanishka Rao, Katya Gonina, Navdeep Jaitly, Bo Li, Jan Chorowski, Michiel Bacchiani
2016	A	`conf`	Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling. INTERSPEECH Ehsan Variani, Tara N. Sainath, Izhak Shafran, Michiel Bacchiani
2016	Misc	`conf`	Factored spatial and spectral multichannel raw waveform CLDNNs. ICASSP Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Arun Narayanan, Michiel Bacchiani
2016	A	`conf`	Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition. INTERSPEECH Bo Li, Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Michiel Bacchiani
2016	A	`conf`	Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction. INTERSPEECH Tara N. Sainath, Arun Narayanan, Ron J. Weiss, Ehsan Variani, Kevin W. Wilson, Michiel Bacchiani, Izhak Shafran
2015	A	`conf`	Large vocabulary automatic speech recognition for children. INTERSPEECH Hank Liao, Golan Pundak, Olivier Siohan, Melissa K. Carroll, Noah Coccaro, Qi-Ming Jiang, Tara N. Sainath, Andrew W. Senior, Françoise Beaufays, Michiel Bacchiani
2015	C	`conf`	Speaker location and microphone spacing invariant acoustic modeling from raw multichannel waveforms. ASRU Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Arun Narayanan, Michiel Bacchiani, Andrew W. Senior
2014	Misc	`conf`	Asynchronous stochastic optimization for sequence training of deep neural networks. ICASSP Georg Heigold, Erik McDermott, Vincent Vanhoucke, Andrew W. Senior, Michiel Bacchiani
2014	A	`conf`	Asynchronous stochastic optimization for sequence training of deep neural networks: towards big data. INTERSPEECH Erik McDermott, Georg Heigold, Pedro J. Moreno, Andrew W. Senior, Michiel Bacchiani
2014	A	`conf`	Asynchronous, online, GMM-free training of a context dependent acoustic model for speech recognition. INTERSPEECH Michiel Bacchiani, Andrew W. Senior, Georg Heigold
2014	Misc	`conf`	Context dependent state tying for speech recognition using deep neural network acoustic models. ICASSP Michiel Bacchiani, David Rybach
2014	Misc	`conf`	GMM-free DNN acoustic model training. ICASSP Andrew W. Senior, Georg Heigold, Michiel Bacchiani, Hank Liao
2014	A	`conf`	Robust speech recognition using temporal masking and thresholding algorithm. INTERSPEECH Chanwoo Kim, Kean K. Chin, Michiel Bacchiani, Richard M. Stern
2013	Misc	`conf`	Rapid adaptation for mobile speech applications. ICASSP Michiel Bacchiani
2013	A	`conf`	ivector-based acoustic data selection. INTERSPEECH Olivier Siohan, Michiel Bacchiani
2011	A	`conf`	Discriminative Features for Language Identification. INTERSPEECH Christopher Alberti, Michiel Bacchiani
2011	J	`jnl`	TechWare: Mobile Media Search Resources [Best of the Web]. IEEE Signal Process. Mag. Zhu Liu, Michiel Bacchiani
2010	A	`conf`	Decision tree state clustering with word and syllable features. INTERSPEECH Hank Liao, Christopher Alberti, Michiel Bacchiani, Olivier Siohan
2009	Misc	`conf`	An audio indexing system for election video material. ICASSP Christopher Alberti, Michiel Bacchiani, Ari Bezman, Ciprian Chelba, Anastassia Drofa, Hank Liao, Pedro J. Moreno, Ted Power, Arnaud Sahuguet, Maria Shugrina, Olivier Siohan
2009	Misc	`conf`	Restoring punctuation and capitalization in transcribed speech. ICASSP Agustín Gravano, Martin Jansche, Michiel Bacchiani
2008	Misc	`conf`	Confidence scores for acoustic model adaptation. ICASSP Christian Gollan, Michiel Bacchiani
2008	Misc	`conf`	Deploying GOOG-411: Early lessons in data, measurement, and testing. ICASSP Michiel Bacchiani, Françoise Beaufays, Johan Schalkwyk, Mike Schuster, Brian Strope
2006	J	`jnl`	MAP adaptation of stochastic grammars. Comput. Speech Lang. Michiel Bacchiani, Michael Riley, Brian Roark, Richard Sproat
2005	A	`conf`	Fast vocabulary-independent audio search using path-based graph indexing. INTERSPEECH Olivier Siohan, Michiel Bacchiani
2004	—	`conf`	Improved name recognition with meta-data dependent name networks. ICASSP (1) Sameer Maskey, Michiel Bacchiani, Brian Roark, Richard Sproat
2004	—	`conf`	Language Model Adaptation with MAP Estimation and the Perceptron Algorithm. HLT-NAACL (Short Papers) Michiel Bacchiani, Brian Roark, Murat Saraclar
2004	—	`conf`	Meta-data conditional language modeling. ICASSP (1) Michiel Bacchiani, Brian Roark
2003	—	`conf`	Supervised and unsupervised PCFG adaptation to novel domains. HLT-NAACL Brian Roark, Michiel Bacchiani
2003	—	`conf`	Unsupervised language model adaptation. ICASSP (1) Michiel Bacchiani, Brian Roark
2002	A	`conf`	Combining maximum likelihood and maximum a posteriori estimation for detailed acoustic modeling of context dependency. INTERSPEECH Michiel Bacchiani
2002	A*	`conf`	SCANMail: a voicemail interface that makes speech browsable, readable and searchable. CHI Steve Whittaker, Julia Hirschberg, Brian Amento, Litza A. Stark, Michiel Bacchiani, Philip L. Isenhour, Larry Stead, Gary Zamchick, Aaron E. Rosenberg
2001	—	`conf`	Audio Browsing and Search in the Voicemail Domain. NLPRS Julia Hirschberg, Michiel Bacchiani, Philip L. Isenhour
2001	Misc	`conf`	Automatic transcription of voicemail at AT&T. ICASSP Michiel Bacchiani
2001	A	`conf`	Caller identification for the SCANMail voicemail browser. INTERSPEECH Aaron E. Rosenberg, Julia Hirschberg, Michiel Bacchiani, Sarangarajan Parthasarathy, Philip L. Isenhour, Larry Stead
2001	—	`conf`	SCANMail: Audio Navigation in the Voicemail Domain. HLT Michiel Bacchiani, Julia Hirschberg, Aaron E. Rosenberg, Steve Whittaker, Donald Hindle, Philip L. Isenhour, Matt Jones, Litza A. Stark, Gary Zamchick
2001	A	`conf`	SCANMail: browsing and searching speech data by content. INTERSPEECH Julia Hirschberg, Michiel Bacchiani, Donald Hindle, Philip L. Isenhour, Aaron E. Rosenberg, Litza A. Stark, Larry Stead, Steve Whittaker, Gary Zamchick
2000	A	`conf`	Using maximum likelihood linear regression for segment clustering and speaker identification. INTERSPEECH Michiel Bacchiani
1999	—	`conf`	AT&T at TREC-8. TREC Amit Singhal, Steven P. Abney, Michiel Bacchiani, Michael Collins, Donald Hindle, Fernando C. N. Pereira
1999	J	`jnl`	Joint lexicon, acoustic unit inventory and model design. Speech Commun. Michiel Bacchiani, Mari Ostendorf
1998	—	`conf`	Using automatically-derived acoustic sub-word units in large vocabulary speech recognition. ICSLP Michiel Bacchiani, Mari Ostendorf
1996	Misc	`conf`	Design of a speech recognition system based on acoustically derived segmental units. ICASSP Michiel Bacchiani, Mari Ostendorf, Yoshinori Sagisaka, Kuldip K. Paliwal
1996	—	`conf`	Speech recognition based on acoustically derived segment units. ICSLP Toshiaki Fukada, Michiel Bacchiani, Kuldip K. Paliwal, Yoshinori Sagisaka
1995	—	`conf`	Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognition. EUROSPEECH Kuldip K. Paliwal, Michiel Bacchiani, Yoshinori Sagisaka
1994	—	`conf`	Optimization of time-frequency masking filters using the minimum classification error criterion. ICASSP (2) Michiel Bacchiani, Kiyoaki Aikawa