Xin Lei

I'm a Research Scientist at Google. I received my PhD in EE from University of Washington at Seattle in 2006, and BS from Tsinghua University in Beijing in 1999. My research interest includes acoustic modeling and fast decoding for large vocabulary speech recognition.

Google Publications

  •  

    Deep Neural Networks for Small Footprint Text-dependent Speaker Verification

    Ehsan Variani, Xin Lei, Erik McDermott, Ignacio Lopez Moreno, Javier Gonzalez-Dominguez

    Proc. ICASSP (2014) (to appear)

  •  

    Fine Context, Low-rank, Softplus Deep Neural Networks for Mobile Speech Recognition

    Andrew Senior, Xin Lei

    Proc. ICASSP (2014) (to appear)

  •   

    Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices

    Xin Lei, Andrew Senior, Alexander Gruenstein, Jeffrey Sorensen

    Interspeech (2013)

  •  

    Deep Neural Networks with Auxiliary Gaussian Mixture Models for Real-Time Speech Recognition

    Xin Lei, Hui Lin, Georg Heigold

    Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE, Vancouver, CA (2013)

  •   

    Unsupervised Testing Strategies for ASR

    Brian Strope, Doug Beeferman, Alexander Gruenstein, Xin Lei

    Interspeech 2011, pp. 1685-1688

Previous Publications

  •  

    Advances in Mandarin Speech-to-Text Transcription for Broadcast News and Conversations

    Xin Lei, Wen Wang, Arindam Mandal, Andreas Stolcke, Mei-Yuh Hwang, Wei Wu, Mari Ostendorf

    Handbook of Natural Language Processing and Machine Translation, Springer (2011)

  •  

    Fast Likelihood Computation Using Hierarchical Gaussian Shortlists

    Xin Lei, Arindam Mandal, Jing Zheng

    Proc. ICASSP (2010)

  •  

    Unsupervised Domain Adaptation with Multiple Acoustic Models

    Xin Lei, Wen Wang, Andreas Stolcke

    Spoken Language Technology Workshop (SLT) (2010)

  •  

    Data-driven Lexicon Expansion for Mandarin Broadcast News and Conversation Speech Recognition

    Xin Lei, Wen Wang, Andreas Stolcke

    Proc. ICASSP (2009)

  •  

    Development of the 2008 SRI Mandarin Speech-to-text System for Broadcast News and Conversation

    Xin Lei, Wei Wu, Wen Wang, Arindam Mandal, Andreas Stolcke

    Proc. Interspeech (2009)

  •  

    Multifactor Adaptation for Mandarin Broadcast News and Conversation Speech Recognition

    Wen Wang, Arindam Mandal, Xin Lei, Jing Zheng, Andreas Stolcke

    Proc. Interspeech (2009)

  •  

    Recent Advances in SRI's IraqComm Iraqi Arabic-English Speech-to-speech Translation System

    Murat Akbacak, Horacio Franco, Michael Frandsen, Sasa Hasan, Huda Jameel, Andreas Kathol, Shahram Khadivi, Xin Lei, Arindam Mandal, Saab Mansour, Kristin Precoda, Colleen Richey, Dimitra Vergyri, Wen Wang, Mei Yang, Jing Zheng

    Proc. ICASSP (2009)

  •  

    Advances in Mandarin Broadcast Speech Recognition

    Mei-Yuh Hwang, Wen Wang, Xin Lei, Jing Zheng, Ozgur Cetin, Gang Peng

    Proc. Interspeech (2007)

  •  

    Combining Discriminative Feature, Transform, and Model Training for Large Vocabulary Speech Recognition

    Jing Zheng, Ozgur Cetin, Mei-Yuh Hwang, Xin Lei, Andreas Stolcke, Nelson Morgan

    Proc. ICASSP (2007)

  •  

    Word-level Tone Modeling for Mandarin Speech Recognition

    Xin Lei, Mari Ostendorf

    Proc. ICASSP (2007)

  •  

    Cross-domain and Cross-language Portability of Acoustic Features Estimated by Multilayer Perceptrons

    Andreas Stolcke, Frantisek Grezl, Mei-Yuh Hwang, Xin Lei, Nelson Morgan, Dimitra Vergyri

    Proc. ICASSP (2006)

  •  

    Improved Tone Modeling for Mandarin Broadcast News Speech Recognition

    Xin Lei, Manhung Siu, Mei-Yuh Hwang, Mari Ostendorf, Tan Lee

    Proc. Interspeech (2006)

  •  

    Investigation on Mandarin Broadcast News Speech Recognition

    Mei-Yuh Hwang, Xin Lei, Wen Wang, Takahiro Shinozaki

    Proc. Interspeech (2006)

  •  

    Modeling Lexical Tones for Mandarin Large Vocabulary Continuous Speech Recognition

    Xin Lei

    Ph.D. Thesis, Department of Electrical Engineering, University of Washington at Seattle (2006)

  •  

    Recent Innovations in Speech-to-Text Transcription at SRI-ICSI-UW

    Andreas Stolcke, Barry Chen, Horacio Franco, Ramana Gadde, Martin Graciarena, Mei-Yuh Hwang, Katrin Kirchhoff, Xin Lei, Arindam Mandal, Nelson Morgan, Tim Ng, Mari Ostendorf, Kemal Sonmez, Anand Venkataraman, Dimitra Vergyri, Wen Wang, Jing Zheng, Qifeng Zhu

    IEEE Transactions on Audio, Speech and Language Processing (2006)

  •  

    Robust Feature Space Adaptation for Telephony Speech Recognition

    Xin Lei, Jon Hamaker, Xiaodong He

    Proc. Interspeech (2006)

  •  

    DBN-based Multi-Stream Mandarin Toneme Recognition

    Xin Lei, Gang Ji, Tim Ng, Jeff Bilmes, Mari Ostendorf

    Proc. ICASSP (2005)

  •  

    Incorporating Tone-related MLP Posteriors in the Feature Representation for Mandarin ASR

    Xin Lei, Mei-Yuh Hwang, Mari Ostendorf

    Proc. Interspeech (2005)

  •  

    Web-data Augmented Language Model for Mandarin Speech Recognition

    Tim Ng, Mari Ostendorf, Mei-Yuh Hwang, Ivan Bulyko, Manhung Siu, Xin Lei

    Proc. ICASSP (2005)

  •  

    Porting Decipher from English to Mandarin

    Mei-Yuh Hwang, Xin Lei, Tim Ng, Mari Ostendorf, Andreas Stolcke, Wen Wang, Jing Zheng, Venkata Ramana Rao Gadde

    DARPA 2004 Rich Transcription Workshop (RT-04) (2004)

  •  

    Progress on Mandarin Conversational Telephone Speech Recognition

    Mei-Yuh Hwang, Xin Lei, Tim Ng, Ivan Bulyko, Mari Ostendorf, Andreas Stolcke, Wen Wang, Jing Zheng, Venkata Ramana Rao Gadde, Martin Graciarena, Man-Hung Siu, Yan Huang

    International Symposium on Chinese Spoken Language Processing (ISCSLP) (2004)