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
(18.226.94.80)
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:
Acoustic Model Optimization for Multilingual Speech Recognition
書刊名:
International Journal of Computational Linguistics & Chinese Language Processing
作者:
Lyu, Dau-cheng
/
Hsu, Chun-nan
/
Chiang, Yuang-chin
/
Lyu, Ren-yuan
出版日期:
2008
卷期:
13:3
頁次:
頁363-385
主題關鍵詞:
Cross-lingual phone set optimization
;
Speech recognition
;
Delta-BIC
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:
3
點閱:21
Due to abundant resources not always being available for resource-limited languages, training an acoustic model with unbalanced training data for multilingual speech recognition is an interesting research issue. In this paper, we propose a three-step data-driven phone clustering method to train a multilingual acoustic model. The first step is to obtain a clustering rule of context independent phone models driven from a well-trained acoustic model using a similarity measurement. For the second step, we further clustered the sub-phone units using hierarchical agglomerative clustering with delta Bayesian information criteria according to the clustering rules. Then, we chose a parametric modeling technique -- model complexity selection -- to adjust the number of Gaussian components in a Gaussian mixture for optimizing the acoustic model between the new phoneme set and the available training data. We used an unbalanced trilingual corpus where the percentages of the amounts of the training sets for Mandarin, Taiwanese, and Hakka are about 60%, 30%, and 10%, respectively. The experimental results show that the proposed sub-phone clustering approach reduced relative syllable error rate by 4.5% over the best result of the decision tree based approach and 13.5% over the best result of the knowledge-based approach.
以文找文
期刊論文
1.
Lyu,Ren-yuan、Liang,Min-siong、Chiang,Yuang-chin(20040800)。Toward Constructing a Multilingual Speech Corpus for Taiwanese (Min-nan), Hakka, and Mandarin。International Journal of Computational Linguistics & Chinese Language Processing,9:2,頁1-12。
2.
Schwarz, Gideon(1978)。Estimating the Dimension of a model。The Annals of Statistics,6(2),461-464。
3.
Fowlkes, E. B.、Mallows, C. L.(1986)。A Method for Comparing Two Hierarchical Clusterings。Journal of the American Statistical Association,78(383),553-584。
4.
Kohler, J.(2001)。Multi-lingual Phone Model for Vocabulary-Independent Speech Recognition Task。International Journal of Speech Communication,35,21-30。
5.
Uebler, U.(2001)。Multi-lingual Speech Recognition in Seven Languages。International Journal of Speech Communication,35,53-69。
會議論文
1.
Anguera, X.、Shinozaki, T.、Wooters, C.、Hernando, J.(2007)。Model Complexity Selection and Cross-Validation EM Training for Robust Speaker Diarization。Honolulu。
2.
Lyu, D. C.、Lyu, R. Y.(2008)。Optimizing The Acoustic Modeling From An Unbalanced Bi-Lingual Corpus。Las Vegas。
3.
Mark, B.、Barnard, E.(1996)。Phone Clustering Using the Bhattacharyya Distance。Philadelphia。2005-2008。
4.
Marthi, B.、Morgan, J.、Peterek, K.、Picone, J.、Wang, W.(1999)。Towards Language Independent Acoustic Modeling。Keystone。
5.
Tritschler, A.、Gopinath, R.(1999)。Improved Speaker Segmentation And Segments Clustering Using The Bayesian Information Criterion672-682。
6.
Wu, Chung-Hsien、Chiu, Y. H.、Shia, C. J.、林君昱(2006)。Phone Set Generation Based On Acoustic and Contextual。Toulouse。
7.
Young, S. J.、Odell, J. J.、Woodland, P. C.(1994)。Tree-based State Tying for High Accuracy Acoustic Modeling。Berling。
圖書
1.
Kirchhoff, K.、Schultz, T.(2006)。Multilingual Speech Processing。
2.
Kumar, C. S.、Mohandas, V. P.、Li, H. Z.(2005)。Multi-lingual Speech Recognition - A Unified Approach。Proc. INTERSPEECH'05。Lisbon。
3.
Liu, Y.、Fung, P.(2005)。Automatic Phone Set Extension with Confidence Measure for Spontaneous Speech。Proc. INTERSPEECH'05。Lisbon。
4.
Lyu, D. C.、Yang, B. H.、Liang, M. S.、Lyu, R. Y.、Hsu, C. N.(2002)。Speaker Independent Acoustic Modeling for Large Vocabulary Bi-lingual Taiwanese/Mandarin Continuous Speech Recognition。Proc SST。Melburne。
5.
Mathews, Robert Henry(1975)。Chinese-English Dictionary。Chinese-English Dictionary。Caves。
其他
1.
Liang, Po-Yu,Shen, J.-L.,Lee, L. S.(1998)。Decision Tree Clustering for Acoustic Modeling in Speaker-Independent Mandarin Telephone Speech Recognition,Singapore。
2.
Young, S. P.,Evermann, G.,Hain, T.,Kershaw, D.,Moore, G.,Odell, J.,Ollason, D.,Povey, D.,Valtchev, V.,Woodland, P.(2002)。The HTK book version 3.2。
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.
Development and Testing of Transcription Software for a Southern Min Spoken Corpus
2.
Data Driven Approaches to Phonetic Transcription with Integration of Automatic Speech Recognition and Grapheme-to-Phoneme for Spoken Buddhist Sutra
3.
Modeling Pronunciation Variation for Bi-Lingual Mandarin/Taiwanese Speech Recognition
4.
Toward Constructing a Multilingual Speech Corpus for Taiwanese (Min-nan), Hakka, and Mandarin
無相關博士論文
無相關書籍
無相關著作
無相關點閱
QR Code