An Investigation of Mixup Training Strategies for Acoustic Models in ASR

Mapping Intimacies ◽

10.21437/interspeech.2018-2191 ◽

2018 ◽

Cited By ~ 1

Author(s):

Ivan Medennikov ◽

Yuri Khokhlov ◽

Aleksei Romanenko ◽

Dmitry Popov ◽

Natalia Tomashenko ◽

...

Keyword(s):

Acoustic Models ◽

Training Strategies

Download Full-text

Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition: A comparison of current training strategies

IEEE Signal Processing Magazine ◽

10.1109/msp.2020.2969859 ◽

2020 ◽

Vol 37 (3) ◽

pp. 39-49

Author(s):

Xiaodong Cui ◽

Wei Zhang ◽

Ulrich Finkler ◽

George Saon ◽

Michael Picheny ◽

...

Keyword(s):

Neural Network ◽

Speech Recognition ◽

Automatic Speech Recognition ◽

Deep Neural Network ◽

Acoustic Models ◽

Distributed Training ◽

Training Strategies

Download Full-text

Introducing Augmentative Communication: Interactive Training Strategies

NSSLHA Journal ◽

10.1044/nsshla_14_68 ◽

1986 ◽

Vol 14 ◽

pp. 68-82

Author(s):

Caroline Musselwhite

Keyword(s):

Augmentative Communication ◽

Interactive Training ◽

Training Strategies

Download Full-text

Part-training strategies in simulated carrier landing final approach training

PsycEXTRA Dataset ◽

10.1037/e574172012-020 ◽

1984 ◽

Author(s):

Dennis C. Wightman ◽

Gavan Lintern

Keyword(s):

Approach Training ◽

Final Approach ◽

Training Strategies

Download Full-text

How Neural Network Depth Compensates for HMM Conditional Independence Assumptions in DNN-HMM Acoustic Models

10.21437/interspeech.2016-283 ◽

2016 ◽

Cited By ~ 1

Author(s):

Suman Ravuri ◽

Steven Wegmann

Keyword(s):

Neural Network ◽

Conditional Independence ◽

Acoustic Models ◽

Independence Assumptions

Download Full-text

Impact of Aliasing on Deep CNN-Based End-to-End Acoustic Models

10.21437/interspeech.2018-1371 ◽

2018 ◽

Cited By ~ 2

Author(s):

Yuan Gong ◽

Christian Poellabauer

Keyword(s):

Acoustic Models ◽

Deep Cnn ◽

End To End

Download Full-text

Supervised Learning of Acoustic Models in a Zero Resource Setting to Improve DPGMM Clustering

10.21437/interspeech.2016-988 ◽

2016 ◽

Cited By ~ 5

Author(s):

Michael Heck ◽

Sakriani Sakti ◽

Satoshi Nakamura

Keyword(s):

Supervised Learning ◽

Acoustic Models ◽

Resource Setting

Download Full-text

Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings

10.21437/interspeech.2016-1161 ◽

2016 ◽

Cited By ~ 5

Author(s):

Masayuki Suzuki ◽

Ryuki Tachibana ◽

Samuel Thomas ◽

Bhuvana Ramabhadran ◽

George Saon

Keyword(s):

Domain Adaptation ◽

Limited Resource ◽

Acoustic Models

Download Full-text

Ensembles of Multi-Scale VGG Acoustic Models

10.21437/interspeech.2017-920 ◽

2017 ◽

Author(s):

Michael Heck ◽

Masayuki Suzuki ◽

Takashi Fukuda ◽

Gakuto Kurata ◽

Satoshi Nakamura

Keyword(s):

Acoustic Models ◽

Multi Scale

Download Full-text

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization

10.21437/interspeech.2017-1129 ◽

2017 ◽

Cited By ~ 1

Author(s):

Xiaodan Zhuang ◽

Arnab Ghoshal ◽

Antti-Veikko Rosti ◽

Matthias Paulik ◽

Daben Liu

Keyword(s):

Acoustic Models ◽

Cross Lingual

Download Full-text

Improved Multilingual Training of Stacked Neural Network Acoustic Models for Low Resource Languages

10.21437/interspeech.2016-1426 ◽

2016 ◽

Cited By ~ 9

Author(s):

Tanel Alumäe ◽

Stavros Tsakalidis ◽

Richard Schwartz

Keyword(s):

Neural Network ◽

Acoustic Models ◽

Low Resource

Download Full-text