Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines
碩士 === 國立中山大學 === 資訊工程學系研究所 === 96 === This thesis proposes an approach to segmenting and identifying mixed-language speech. Automatic LID can be divided into four steps, feature extraction, segmentation, segment clustering, and re-labeling. In feature extraction, we compare the group delay...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2008
|
Online Access: | http://ndltd.ncl.edu.tw/handle/rv6bmu |
id |
ndltd-TW-096NSYS5392078 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-096NSYS53920782018-05-18T04:28:47Z http://ndltd.ncl.edu.tw/handle/rv6bmu Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines 使用差分貝氏資訊準則及支援向量機於混合語言語音自動分段與辨識 Sheng-Fu Wang 王聖富 碩士 國立中山大學 資訊工程學系研究所 96 This thesis proposes an approach to segmenting and identifying mixed-language speech. Automatic LID can be divided into four steps, feature extraction, segmentation, segment clustering, and re-labeling. In feature extraction, we compare the group delay feature (GDF) with MFCC feature. Unlike the traditional feature from Fourier trans-form magnitude, GDF uses the phase spectrum. In segmentation, we compare delta Bayesian information criterion (delta-BIC) with support vector machines (SVMs). A delta-BIC is applied to segment the input speech utterance into a sequence of lan-guage-dependent segments using acoustic features. The segments are clustered using the K-means algorithm. Finally, re-labeling is used to determine the language of the clusters. SVMs proceed to segment and identify automatically after model training. Considering the effect of the accent issue, we use the corpus English Across Taiwan (EAT) to perform our system. The experimental results show that the system can reach 78.13% in the frame hit rate under the baseline 57.77%. Chia-Ping Chen 陳嘉平 2008 學位論文 ; thesis 66 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中山大學 === 資訊工程學系研究所 === 96 === This thesis proposes an approach to segmenting and identifying mixed-language speech.
Automatic LID can be divided into four steps, feature extraction, segmentation, segment clustering, and re-labeling. In feature extraction, we compare the group delay feature (GDF) with MFCC feature. Unlike the traditional feature from Fourier trans-form magnitude, GDF uses the phase spectrum. In segmentation, we compare delta Bayesian information criterion (delta-BIC) with support vector machines (SVMs). A delta-BIC is applied to segment the input speech utterance into a sequence of lan-guage-dependent segments using acoustic features. The segments are clustered using the K-means algorithm. Finally, re-labeling is used to determine the language of the clusters. SVMs proceed to segment and identify automatically after model training.
Considering the effect of the accent issue, we use the corpus English Across Taiwan (EAT) to perform our system. The experimental results show that the system can reach 78.13% in the frame hit rate under the baseline 57.77%.
|
author2 |
Chia-Ping Chen |
author_facet |
Chia-Ping Chen Sheng-Fu Wang 王聖富 |
author |
Sheng-Fu Wang 王聖富 |
spellingShingle |
Sheng-Fu Wang 王聖富 Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
author_sort |
Sheng-Fu Wang |
title |
Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
title_short |
Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
title_full |
Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
title_fullStr |
Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
title_full_unstemmed |
Automatic Segmentation and Identification of Mixed-Language Speech Using delta-BIC and Support Vector Machines |
title_sort |
automatic segmentation and identification of mixed-language speech using delta-bic and support vector machines |
publishDate |
2008 |
url |
http://ndltd.ncl.edu.tw/handle/rv6bmu |
work_keys_str_mv |
AT shengfuwang automaticsegmentationandidentificationofmixedlanguagespeechusingdeltabicandsupportvectormachines AT wángshèngfù automaticsegmentationandidentificationofmixedlanguagespeechusingdeltabicandsupportvectormachines AT shengfuwang shǐyòngchàfēnbèishìzīxùnzhǔnzéjízhīyuánxiàngliàngjīyúhùnhéyǔyányǔyīnzìdòngfēnduànyǔbiànshí AT wángshèngfù shǐyòngchàfēnbèishìzīxùnzhǔnzéjízhīyuánxiàngliàngjīyúhùnhéyǔyányǔyīnzìdòngfēnduànyǔbiànshí |
_version_ |
1718640712237449216 |