Improved spoken term detection by discriminative training of acoustic models based on user relevance feedback

Mapping Intimacies ◽

10.21437/interspeech.2010-400 ◽

2010 ◽

Author(s):

Hung-yi Lee ◽

Chia-ping Chen ◽

Ching-feng Yeh ◽

Lin-shan Lee

Keyword(s):

Relevance Feedback ◽

Discriminative Training ◽

Spoken Term Detection ◽

Acoustic Models

Download Full-text

Intensive acoustic models constructed by integrating low-occurrence models for spoken term detection

10.21437/interspeech.2013-6 ◽

2013 ◽

Author(s):

Shiro Narumi ◽

Kazuma Konno ◽

Takuya Nakano ◽

Yoshiaki Itoh ◽

Kazunori Kojima ◽

...

Keyword(s):

Spoken Term Detection ◽

Acoustic Models

Download Full-text

Training data selection for improving discriminative training of acoustic models

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU) ◽

10.1109/asru.2007.4430125 ◽

2007 ◽

Author(s):

Shih-Hung Liu ◽

Fang-Hui Chu ◽

Shih-Hsiang Lin ◽

Hung-Shin Lee ◽

Berlin Chen

Keyword(s):

Discriminative Training ◽

Training Data ◽

Data Selection ◽

Acoustic Models ◽

Selection For ◽

Training Data Selection

Download Full-text

Adaptation and Discriminative Training of Acoustic Models

Techniques for Noise Robustness in Automatic Speech Recognition ◽

10.1002/9781118392683.ch11 ◽

2012 ◽

pp. 283-310 ◽

Author(s):

Yannick Estève ◽

Paul Deléglise

Keyword(s):

Discriminative Training ◽

Acoustic Models

Download Full-text

A regularized discriminative training method of acoustic models derived by minimum relative entropy discrimination

10.21437/interspeech.2010-27 ◽

2010 ◽

Author(s):

Yotaro Kubo ◽

Shinji Watanabe ◽

Atsushi Nakamura ◽

Tetsunori Kobayashi

Keyword(s):

Relative Entropy ◽

Discriminative Training ◽

Training Method ◽

Acoustic Models ◽

Minimum Relative Entropy

Download Full-text

Discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition

2009 IEEE International Conference on Acoustics, Speech and Signal Processing ◽

10.1109/icassp.2009.4960625 ◽

2009 ◽

Author(s):

Hung-An Chang ◽

James R. Glass

Keyword(s):

Speech Recognition ◽

Discriminative Training ◽

Continuous Speech ◽

Continuous Speech Recognition ◽

Large Vocabulary ◽

Acoustic Models

Download Full-text

A framework integrating different relevance feedback scenarios and approaches for spoken term detection

2010 IEEE Spoken Language Technology Workshop ◽

10.1109/slt.2010.5700884 ◽

2010 ◽

Author(s):

Hung-yi Lee ◽

Chia-ping Chen ◽

Ching-feng Yeh ◽

Lin-shan Lee

Keyword(s):

Relevance Feedback ◽

Spoken Term Detection

Download Full-text

A distributed architecture for fast SGD sequence discriminative training of DNN acoustic models

2014 IEEE Spoken Language Technology Workshop (SLT) ◽

10.1109/slt.2014.7078571 ◽

2014 ◽

Author(s):

George Saon

Keyword(s):

Discriminative Training ◽

Distributed Architecture ◽

Acoustic Models

Download Full-text

Leveraging Unlabeled Speech for Sequence Discriminative Training of Acoustic Models

10.21437/interspeech.2020-2056 ◽

2020 ◽

Author(s):

Ashtosh Sapru ◽

Sri Garimella

Keyword(s):

Discriminative Training ◽

Acoustic Models

Download Full-text

Discriminative Training of Gender-Dependent Acoustic Models

Text, Speech and Dialogue - Lecture Notes in Computer Science ◽

10.1007/978-3-642-04208-9_46 ◽

2009 ◽

pp. 331-338 ◽

Author(s):

Jan Vaněk ◽

Josef V. Psutka ◽

Jan Zelinka ◽

Aleš Pražák ◽

Josef Psutka

Keyword(s):

Discriminative Training ◽

Acoustic Models

Download Full-text

Improved spoken term detection using support vector machines with acoustic and context features from pseudo-relevance feedback

2011 IEEE Workshop on Automatic Speech Recognition & Understanding ◽

10.1109/asru.2011.6163962 ◽

2011 ◽

Author(s):

Tsung-wei Tu ◽

Hung-yi Lee ◽

Lin-shan Lee

Keyword(s):

Support Vector Machines ◽

Relevance Feedback ◽

Support Vector ◽

Spoken Term Detection ◽

Vector Machines ◽

Context Features ◽

Pseudo Relevance Feedback

Download Full-text