抄録
Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2nd 'CHiME' Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings |
| ページ | 6935-6939 |
| ページ数 | 5 |
| DOI | |
| 出版物ステータス | Published - 2013 10 18 |
| 外部発表 | Yes |
| イベント | 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC 継続期間: 2013 5 26 → 2013 5 31 |
Other
| Other | 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 |
|---|---|
| 市 | Vancouver, BC |
| 期間 | 13/5/26 → 13/5/31 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Software
- Electrical and Electronic Engineering
これを引用
Effectiveness of discriminative training and feature transformation for reverberated and noisy speech. / Tachioka, Yuuki; Watanabe, Shinji; Hershey, John R.
2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 6935-6939 6639006.研究成果: Conference contribution
}
TY - GEN
T1 - Effectiveness of discriminative training and feature transformation for reverberated and noisy speech
AU - Tachioka, Yuuki
AU - Watanabe, Shinji
AU - Hershey, John R.
PY - 2013/10/18
Y1 - 2013/10/18
N2 - Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2nd 'CHiME' Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline.
AB - Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2nd 'CHiME' Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline.
KW - Augmented discriminative feature transformation
KW - CHiME challenge
KW - Discriminative training
KW - Feature transformation
KW - Kaldi
UR - http://www.scopus.com/inward/record.url?scp=84890503970&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84890503970&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2013.6639006
DO - 10.1109/ICASSP.2013.6639006
M3 - Conference contribution
AN - SCOPUS:84890503970
SN - 9781479903566
SP - 6935
EP - 6939
BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
ER -