資料載入處理中...
臺灣人文及社會科學引文索引資料庫系統
:::
網站導覽
國圖首頁
聯絡我們
操作說明
English
行動版
(18.216.134.4)
登入
字型:
**字體大小變更功能,需開啟瀏覽器的JAVASCRIPT,如您的瀏覽器不支援,
IE6請利用鍵盤按住ALT鍵 + V → X → (G)最大(L)較大(M)中(S)較小(A)小,來選擇適合您的文字大小,
如為IE7以上、Firefoxy或Chrome瀏覽器則可利用鍵盤 Ctrl + (+)放大 (-)縮小來改變字型大小。
來源文獻查詢
引文查詢
瀏覽查詢
作者權威檔
引用/點閱統計
我的研究室
資料庫說明
相關網站
來源文獻查詢
/
簡易查詢
/
查詢結果列表
/
詳目列表
:::
詳目顯示
第 1 筆 / 總合 1 筆
/1
頁
來源文獻資料
外文摘要
引文資料
題名:
An Empirical Study of Word Error Minimization Approaches for Mandarin Large Vocabulary Continuous Speech Recognition
書刊名:
International Journal of Computational Linguistics & Chinese Language Processing
作者:
Kuo, Jen-wei
/
Liu, Shih-hung
/
Wang, Hsin-min
/
Chen, Berlin
出版日期:
2006
卷期:
11:3
頁次:
頁201-222
主題關鍵詞:
Broadcast news
;
Continuous speech recognition
;
Discriminative training
;
Minimum phone error
;
Word error minimization
原始連結:
連回原系統網址
相關次數:
被引用次數:期刊(0) 博士論文(0) 專書(0) 專書論文(0)
排除自我引用:0
共同引用:
8
點閱:24
This paper presents and empirical study of word error minimization approaches for Mandarin large vocabulary continuous speech recognition (LVCSR). First, the minimum phone error (MPE) criterion, which is one of the most popular discriminative training criteria, is extensively investigated for both acoustic model training and adaptation in a Mandarin LVCSR system. Second, the word error minimization (WEM) criterion, used to rescore N-best word strings, is appropriately modified for a Mandarin LVCSR system. Finally, a series of speech recognition experiments is conducted on the MATBN Mandarin Chinese broadcast news corpus. The experiment results demonstrate that the MPE training approach reduces the character error rate (CER) by 12% for a system initially trained with the maximum likelihood (ML) approach. Meanwhile, for unsupervised acoustic model adaptation, MPE-based linear regression (MPELR) adaptation outperforms conventional maximum likelihood linear regression (MLLR) in terms of CER reduction. When the WEM decoding approach is used for N-based rescoring, a slight performance gain over the conventional maximum a posteriori (MAP) decoding method is also observed.
以文找文
期刊論文
1.
Leggetter, C. J.、Woodland, P. C.(1995)。Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models。Computer Speech and Language,9(2),171-185。
2.
Wang, Hsin-min、Chen, Berlin、Kuo, Jen-wei、Cheng, Shih-sian(20050600)。MATBN: A Mandarin Chinese Broadcast News Corpus。International Journal of Computational Linguistics & Chinese Language Processing,10(2),219-235。
3.
Levenshtein, V. I.(1966)。Binary codes capable of correcting deletions, insertions and reversals。Soviet Physics Doklady,10(8),707-710。
4.
Gales, M. J. F.、Woodland, P. C.(1996)。Mean and Variance Adaptation within the MLLR Framework。Computer Speech and Language,10,249-264。
5.
Ortmanns, S.、Ney, H.、Aubert, X. L.(1997)。A Word Graph Algorithm for Large Vocabulary Continuous Speech Recognition。Computer Speech and Language,11,43-72。
6.
Chen, B.、Kuo, J. W.、Tsai, W. H.(2005)。Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription。中文計算語言學期刊,10(1),1-18。
7.
Goel, Vinod、Byrne, W.(2000)。Minimum Bayes-Risk Automatic Speech Recognition。Computer Speech and Language,14,115-135。
8.
Gopalakrishnan, P.S.、Kanevsky, D.、Nádas, A.、Nahamoo, D.(1991)。An Inequality for Rational Functions with Applications to Some Statistical Estimation Problems。IEEE Trans. Information Theory,37,107-133。
9.
Kaiser, J.、Horvat, B.、Kacic, Z.(2000)。Overall Risk Criterion Estimation of Hidden Maekov Model Parameters。Speech Communication,38,383-398。
10.
Mangu, L.、Brill, E.、Stolcke, A.(2000)。Finding consensus in speech recognition: word error minimization and other applications of confusion networks。Computer Speech and Language,14,373-400。
11.
Povey, D.、Woodland, P. C.(2002)。Large Scale Discriminative Training of Acoustic Models for Speech Recognition。Computer Speech and Language,16,25-47。
會議論文
1.
Chien, J. T.、Huang, C. H.、Shinoda, K.、Furui, S.(2006)。Towards Optimal Bayes Decision for Speech Recognition。Toulouse, France。
2.
Kuo, J. W.、Chen, B.(2005)。Minimum Word error Based Discriminative Training of Language Models。Lisbon。1277-1280。
學位論文
1.
Povey, D.(2004)。Discriminative Training for Large Vocabulary Speech Recognition,Peterhouse。
2.
郭人瑋(2005)。An Initial Study on Minimum Phone Error Discriminative Learning of Acoustic Models for Mandarin Large Vocabulary Continuous Speech Recognition,Taipei。
3.
Normandin, Y.(1991)。Hidden Markov Models, Maximum Mutual Information Estimation, and the Speech Recognition Proble,Montreal。
圖書
1.
Duda, R. D.、Hart, P. E.、Stork, D. G.(2000)。Pattern Classification。Pattern Classification。New York。
2.
Zheng, J.、Stolcke, A.(2005)。Improved Discriminative Training Using Phone Lattices。Proc. INTERSPEECH'05。Lisbon。
其他
1.
Doumpiotis, V.,Tsakalidis, S.,Byrne, W.(2003)。Discriminative Training for Segmental Minimum Bayes Risk Decoding,Hong Kong。
2.
Doumpiotis, V.,Tsakalidis, S.,Byrne, W.(2003)。Lattice Segmentation and Minimum Bayes Risk Discriminative Training。
3.
Doumpiotis, V.,Byrne, W.(2004)。Pinched Lattice Minimum Bayes Risk Discriminative Training for Large Vocabulary Continuous Speech Recognition,Jeju Island, Korea。
4.
Kaiser, J.,Horvat, B.,Kacic, Z.(2000)。A Novel Loss Function for the Overall Risk Criterion Based Discriminative Training of HMM Models。
5.
Na, K.,Jeon, B.,Chang, D.,Chae, S.,Ann, S.(1995)。Discriminative Training of Hidden Markov Models using Overall Risk Criterion and Reduced Gradient Method,Madrid。
6.
Povey, D.,Woodland, P. C.(2002)。Minimum Phone Error and I-smoothing for Improved Discriminative Training。
7.
Povey, D.,Kingsbury, B.,Mangu, L.,Saon, G.,Soltau, H.,Zweig, G.(2005)。FMPE: Discriminatively Trained Features for Speech Recognition,Philadelphia, USA。
8.
Schlüter, R.,Scharrenbach, T.,Steinbiss, V.,Ney, H.(2005)。Bayes Risk Minimization using Metric Loss Functions。
9.
Schwartz, R.,Chow, Y. L.(1990)。The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypotheses。
10.
Stolcke, A.,Konig, Y.,Weintraub, M.(1997)。Explict Word Error Minimization in N-best List Rescoring。
11.
Stolcke, A.(2000)。SRI language Modeling Toolkit。
12.
Wang, L.,Woodland, P. C.(2004)。MPE-Based Discriminative Linear Transform for Speaker Adaptation,Montreal, Canada。
推文
當script無法執行時可按︰
推文
推薦
當script無法執行時可按︰
推薦
引用網址
當script無法執行時可按︰
引用網址
引用嵌入語法
當script無法執行時可按︰
引用嵌入語法
轉寄
當script無法執行時可按︰
轉寄
top
:::
相關期刊
相關論文
相關專書
相關著作
熱門點閱
1.
基於端對端模型化技術之語音文件摘要
2.
基於特徵粒度之訓練策略於中文口語問答系統之應用
3.
結合鑑別式訓練聲學模型之類神經網路架構及優化方法的改進
4.
當代非監督式方法之比較於節錄式語言摘要
5.
融合多任務學習類神經網路聲學模型訓練於會議語音辨識之研究
6.
節錄式語音文件摘要使用表示法學習技術
7.
使用概念資訊於中文大詞彙連續語音辨識之研究
8.
Improved Minimum Phone Error Based Discriminative Training of Acoustic Models for Mandarin Large Vocabulary Continuous Speech Recognition
9.
MATBN: A Mandarin Chinese Broadcast News Corpus
無相關博士論文
無相關書籍
無相關著作
無相關點閱
QR Code