Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing

被引：0

作者：

Cui, Xiaodong ^{[1
]}

Saon, George ^{[1
]}

Nagano, Tohru ^{[2
]}

Suzuki, Masayuki ^{[2
]}

Fukuda, Takashi ^{[2
]}

Kingsbury, Brian ^{[1
]}

Kurata, Gakuto ^{[2
]}

机构：

[1] IBM Research AI, IBM T. J. Watson Research Center, United States

[2] IBM Research Tokyo, Japan

来源：

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 2022年 / 2022-September卷

关键词：

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Perturbation techniques - Recurrent neural networks - Speech communication - Speech recognition

引用

页码：2638 / 2642

共 22 条

[11] Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training
Narayanan, Arun
Wang, DeLiang
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2015, 23 (01) : 92 - 101
[12] Context adaptive neural network for rapid adaptation of deep CNN based acoustic models
Delcroix, Marc
Kinoshita, Keisuke
Ogawa, Atsunori
Yoshioka, Takuya
Tran, Dung
Nakatani, Tomohiro
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1573 - 1577
[13] Cluster-Based Senone Selection for the Efficient Calculation of Deep Neural Network Acoustic Models
Liu, Jun-Hua
Ling, Zhen-Hua
Wei, Si
Hu, Guo-Ping
Dai, Li-Rong
2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
[14] Architectures for deep neural network based acoustic models defined over windowed speech waveforms
Bhargava, Mayank
Rose, Richard
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 6 - 10
[15] Prefix Tree based N-best list Re-scoring for Recurrent Neural Network Language Model used in Speech Recognition System
Si, Yujing
Zhang, Qingqing
Li, Ta
Pan, Jielin
Yan, Yonghong
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 3386 - 3390
[16] IMPROVING NOISE ROBUSTNESS FOR SPOKEN CONTENT RETRIEVAL USING SEMI-SUPERVISED ASR AND N-BEST TRANSCRIPTS FOR BERT-BASED RANKING MODELS
Moriya, Yasufumi
Jones, Gareth. J. F.
2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 398 - 405
[17] Parameter Reduction For Deep Neural Network Based Acoustic Models Using Sparsity Regularized Factorization Neurons
Chung, Hoon
Chung, Euisok
Park, Jeon Gue
Jung, Ho-Young
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
[18] Ensemble of jointly trained deep neural network-based acoustic models for reverberant speech recognition
Lee, Moa
Lee, Jeehye
Chang, Joon-Hyuk
DIGITAL SIGNAL PROCESSING, 2019, 85 : 1 - 9
[19] Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers
Hu, Wenping
Qian, Yao
Soong, Frank K.
Wang, Yong
SPEECH COMMUNICATION, 2015, 67 : 154 - 166
[20] Automatic assessment of English proficiency for Japanese learners without reference sentences based on deep neural network acoustic models
Fu, Jiang
Chiba, Yuya
Nose, Takashi
Ito, Akinori
SPEECH COMMUNICATION, 2020, 116 : 86 - 97

← 1 2 3 →