M
Michiel Bacchiani
Researcher at Google
Publications - 91
Citations - 4876
Michiel Bacchiani is an academic researcher from Google. The author has contributed to research in topics: Acoustic model & Word error rate. The author has an hindex of 34, co-authored 86 publications receiving 3970 citations. Previous affiliations of Michiel Bacchiani include IBM & Boston University.
Papers
More filters
Proceedings ArticleDOI
State-of-the-Art Speech Recognition with Sequence-to-Sequence Models
Chung-Cheng Chiu,Tara N. Sainath,Yonghui Wu,Rohit Prabhavalkar,Patrick Nguyen,Zhifeng Chen,Anjuli Kannan,Ron Weiss,Kanishka Rao,Ekaterina Gonina,Navdeep Jaitly,Bo Li,Jan Chorowski,Michiel Bacchiani +13 more
TL;DR: In this article, the authors explore a variety of structural and optimization improvements to the Listen, Attend, and Spell (LAS) encoder-decoder architecture, which significantly improves performance.
Proceedings ArticleDOI
Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home
Chanwoo Kim,Ananya Misra,K. K. Chin,Thad Hughes,Arun Narayanan,Tara N. Sainath,Michiel Bacchiani +6 more
TL;DR: The structure and application of an acoustic room simulator to generate large-scale simulated data for training deep neural networks for far-field speech recognition and performance is evaluated using a factored complex Fast Fourier Transform (CFFT) acoustic model introduced in earlier work.
Journal ArticleDOI
Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition
Tara N. Sainath,Ron Weiss,Kevin W. Wilson,Bo Li,Arun Narayanan,Ehsan Variani,Michiel Bacchiani,Izhak Shafran,Andrew W. Senior,Kean Chin,Ananya Misra,Chanwoo Kim +11 more
TL;DR: This paper introduces a neural network architecture, which performs multichannel filtering in the first layer of the network, and shows that this network learns to be robust to varying target speaker direction of arrival, performing as well as a model that is given oracle knowledge of the true target Speaker direction.
Posted Content
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
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 Marie Laurenzo,James Qin,Orhan Firat,Wolfgang Macherey,Suyog Gupta,Ankur Bapna,Shuyuan Zhang,Ruoming Pang,Ron 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 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 N. 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 +90 more
TL;DR: This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the Framework.
Proceedings ArticleDOI
Acoustic Modeling for Google Home
Bo Li,Tara N. Sainath,Arun Narayanan,J. Caroselli,Michiel Bacchiani,Ananya Misra,Izhak Shafran,Hasim Sak,Golan Pundak,K. K. Chin,Khe Chai Sim,Ron Weiss,Kevin W. Wilson,Ehsan Variani,Chanwoo Kim,Olivier Siohan,Mitchel Weintraub,Erik McDermott,Richard Rose,Matt Shannon +19 more
TL;DR: The technical and system building advances made to the Google Home multichannel speech recognition system, which was launched in November 2016, result in a reduction of WER of 8-28% relative to the current production system.