Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments
碩士 === 元智大學 === 通訊工程學系 === 99 === To detect speech-block end-points, we use entropy of the speech signal, and compare the t of two weighted linear models for the entropy. The regression models are constructed so that their t will di er the most near the speech-block end-points. For estimation of s...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/55990173986262954692 |
id |
ndltd-TW-099YZU05650043 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099YZU056500432016-04-13T04:17:17Z http://ndltd.ncl.edu.tw/handle/55990173986262954692 Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments 基於階層式線性模型比較與熵參數之語音區塊端點偵測 Ming-Chaing Hsu 徐明江 碩士 元智大學 通訊工程學系 99 To detect speech-block end-points, we use entropy of the speech signal, and compare the t of two weighted linear models for the entropy. The regression models are constructed so that their t will di er the most near the speech-block end-points. For estimation of speech signal entropy we use a histogram of speech signal that is sampled in a frame of xed duration. The resulting sequence of entropies in consecutive frames is used for tting the linear models. The models are tted in a sliding interval of the entropies, that correspond to several consecutive frames in a sliding time window. The interval with the greatest di erence of the model t is used to estimate the location of the speech-block boundaries. Model M1 is very simple; it corresponds to a constant average entropy level for the speech signal in the entire window. Model M2 models step-like entropy change from one constant level to another, with a gradual transition between the levels. It is a piecewise linear regression model with two horizontal lines connected by a third transitional line. We treat M1 as a linear model only to be able to describe it as a sub-model of M2 and use statistical methodology for sub-model testing. The performance of the presented algorithm is compared with a standard EOU (end-of-utterance) detection. The average rate of proper detection is 92.36% for our approach. It gets almost 13% improvement over the EOU method. Several tables are presented to illustrate that, while obtaining similar result for clean sound, our regression model approach has better ability to resist the negative e ect of noise. Wei-Tyng Hong 洪維廷 2011 學位論文 ; thesis 72 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 元智大學 === 通訊工程學系 === 99 === To detect speech-block end-points, we use entropy of the speech signal, and compare
the t of two weighted linear models for the entropy. The regression models are
constructed so that their t will di er the most near the speech-block end-points.
For estimation of speech signal entropy we use a histogram of speech signal that
is sampled in a frame of xed duration. The resulting sequence of entropies in
consecutive frames is used for tting the linear models. The models are tted in a
sliding interval of the entropies, that correspond to several consecutive frames in a
sliding time window. The interval with the greatest di erence of the model t is
used to estimate the location of the speech-block boundaries.
Model M1 is very simple; it corresponds to a constant average entropy level for
the speech signal in the entire window. Model M2 models step-like entropy change
from one constant level to another, with a gradual transition between the levels. It
is a piecewise linear regression model with two horizontal lines connected by a third
transitional line. We treat M1 as a linear model only to be able to describe it as a
sub-model of M2 and use statistical methodology for sub-model testing.
The performance of the presented algorithm is compared with a standard EOU
(end-of-utterance) detection. The average rate of proper detection is 92.36% for our
approach. It gets almost 13% improvement over the EOU method. Several tables
are presented to illustrate that, while obtaining similar result for clean sound, our
regression model approach has better ability to resist the negative e ect of noise.
|
author2 |
Wei-Tyng Hong |
author_facet |
Wei-Tyng Hong Ming-Chaing Hsu 徐明江 |
author |
Ming-Chaing Hsu 徐明江 |
spellingShingle |
Ming-Chaing Hsu 徐明江 Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
author_sort |
Ming-Chaing Hsu |
title |
Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
title_short |
Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
title_full |
Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
title_fullStr |
Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
title_full_unstemmed |
Robust Hierarchical Linear Model Comparison forUtterance-End Detection Under Noisy Environments |
title_sort |
robust hierarchical linear model comparison forutterance-end detection under noisy environments |
publishDate |
2011 |
url |
http://ndltd.ncl.edu.tw/handle/55990173986262954692 |
work_keys_str_mv |
AT mingchainghsu robusthierarchicallinearmodelcomparisonforutteranceenddetectionundernoisyenvironments AT xúmíngjiāng robusthierarchicallinearmodelcomparisonforutteranceenddetectionundernoisyenvironments AT mingchainghsu jīyújiēcéngshìxiànxìngmóxíngbǐjiàoyǔshāngcānshùzhīyǔyīnqūkuàiduāndiǎnzhēncè AT xúmíngjiāng jīyújiēcéngshìxiànxìngmóxíngbǐjiàoyǔshāngcānshùzhīyǔyīnqūkuàiduāndiǎnzhēncè |
_version_ |
1718222775151230976 |