A fast algorithm for parallel model combination for noisy speech recognition

Computer Speech & Language ◽

10.1006/csla.2000.0137 ◽

2000 ◽

Vol 14 (2) ◽

pp. 81-100 ◽

Author(s):

Tai-Hwei Hwang ◽

Hsiao-Chuan Wang

Keyword(s):

Speech Recognition ◽

Fast Algorithm ◽

Parallel Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text

An improved parallel model combination method for noisy speech recognition

2009 IEEE Workshop on Automatic Speech Recognition & Understanding ◽

10.1109/asru.2009.5373332 ◽

2009 ◽

Author(s):

Hadi Veisi ◽

Hossein Sameti

Keyword(s):

Speech Recognition ◽

Combination Method ◽

Parallel Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text

A Trajectory-based Parallel Model Combination with a unified static and dynamic parameter compensation for noisy speech recognition

2011 IEEE Workshop on Automatic Speech Recognition & Understanding ◽

10.1109/asru.2011.6163914 ◽

2011 ◽

Author(s):

Khe Chai Sim ◽

Minh-Thang Luong

Keyword(s):

Speech Recognition ◽

Dynamic Parameter ◽

Parallel Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition ◽

Parameter Compensation

Download Full-text

Adaptive Parallel Model Combination for reduced environmental mismatch in noisy speech recognition

10.1109/iced.2008.4786758 ◽

2008 ◽

Author(s):

S. S. Tan ◽

Abdul Manan Ahmad

Keyword(s):

Speech Recognition ◽

Parallel Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text

Cepstrum-domain model combination based on decomposition of speech and noise for noisy speech recognition

IEEE International Conference on Acoustics Speech and Signal Processing ◽

10.1109/icassp.2002.5743691 ◽

2002 ◽

Author(s):

Hong Kook Kim ◽

Richard C. Rose

Keyword(s):

Speech Recognition ◽

Domain Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text

Cepstrum-domain model combination based on decomposition of speech and noise for noisy speech recognition

IEEE International Conference on Acoustics Speech and Signal Processing ◽

10.1109/icassp.2002.1005713 ◽

2002 ◽

Author(s):

Hong Kook Kim ◽

Rose

Keyword(s):

Speech Recognition ◽

Domain Model ◽

Model Combination ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text

Joint Optimization of Denoising Autoencoder and DNN Acoustic Model Based on Multi-Target Learning for Noisy Speech Recognition

10.21437/interspeech.2016-388 ◽

2016 ◽

Author(s):

Masato Mimura ◽

Shinsuke Sakai ◽

Tatsuya Kawahara

Keyword(s):

Speech Recognition ◽

Joint Optimization ◽

Acoustic Model ◽

Denoising Autoencoder ◽

Noisy Speech ◽

Model Based ◽

Noisy Speech Recognition

Download Full-text

Noisy speech recognition based on HMMs, Wiener filters and re-evaluation of most likely candidates

IEEE International Conference on Acoustics Speech and Signal Processing ◽

10.1109/icassp.1993.319241 ◽

1993 ◽

Author(s):

S.V. Vaseghi ◽

B.P. Milner

Keyword(s):

Speech Recognition ◽

Noisy Speech ◽

Wiener Filters ◽

Noisy Speech Recognition

Download Full-text

A novel classifier modification approach to missing data problem for noisy speech recognition

7'th International Symposium on Telecommunications (IST'2014) ◽

10.1109/istel.2014.7000747 ◽

2014 ◽

Author(s):

Kian Ebrahim Kafoori ◽

Seyed Mohammad Ahadi

Keyword(s):

Speech Recognition ◽

Missing Data ◽

Noisy Speech ◽

Missing Data Problem ◽

Data Problem ◽

Noisy Speech Recognition

Download Full-text

Word Graph Based Feature Enhancement for Noisy Speech Recognition

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07 ◽

10.1109/icassp.2007.366927 ◽

2007 ◽

Author(s):

Zhi-Jie Yan ◽

Frank K. Soong ◽

Ren-Hua Wang

Keyword(s):

Speech Recognition ◽

Noisy Speech ◽

Feature Enhancement ◽

Noisy Speech Recognition

Download Full-text

Unsupervised Beamforming Based on Multichannel Nonnegative Matrix Factorization for Noisy Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp.2018.8462642 ◽

2018 ◽

Author(s):

Kazuki Shimada ◽

Yoshiaki Bando ◽

Masato Mimura ◽

Katsutoshi Itoyama ◽

Kazuyoshi Yoshii ◽

...

Keyword(s):

Speech Recognition ◽

Matrix Factorization ◽

Nonnegative Matrix Factorization ◽

Nonnegative Matrix ◽

Noisy Speech ◽

Noisy Speech Recognition

Download Full-text