<abstract xmlns="http://www.w3.org/1999/xhtml"><p> This paper proposes a new contour-based speech endpoint detector which combines the log-Group Delay Mean-Delta (log-GDMD) feature, an adaptive twothreshold scheme and an eight-state automaton. The adaptive thresholds scheme uses two pairs of thresholds - for the starting and for the ending points, respectively. Each pair of thresholds is calculated by using the contour characteristics in the corresponded region of the utterance. The experimental results have shown that the proposed detector demonstrates better performance compared to the Long-Term Spectral Divergence (LTSD) one in terms of endpoint accuracy. Additional fixed-text speaker verification tests with short phrases of telephone speech based on the Dynamic Time Warping (DTW) and left-to-right Hidden Markov Model (HMM) frameworks confirm the improvements of the verification rate due to the better endpoint accuracy.</p></abstract>

This paper proposes a new contour-based speech endpoint detector which combines the log-Group Delay Mean-Delta (log-GDMD) feature, an adaptive twothreshold scheme and an eight-state automaton. The adaptive thresholds scheme uses two pairs of thresholds - for the starting and for the ending points, respectively. Each pair of thresholds is calculated by using the contour characteristics in the corresponded region of the utterance. The experimental results have shown that the proposed detector demonstrates better performance compared to the Long-Term Spectral Divergence (LTSD) one in terms of endpoint accuracy. Additional fixed-text speaker verification tests with short phrases of telephone speech based on the Dynamic Time Warping (DTW) and left-to-right Hidden Markov Model (HMM) frameworks confirm the improvements of the verification rate due to the better endpoint accuracy.

LTSD and GDMD features for Telephone Speech Endpoint Detection

Cybernetics and Information Technologies

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"LTSD and GDMD features for Telephone Speech Endpoint Detection"}

This paper proposes a new contour-based speech endpoint detector which combines the log-Group Delay Mean-Delta (log-GDMD) feature, an adaptive twothreshold...

LTSD and GDMD features for Telephone Speech Endpoint Detection

Data publikacji: 30 lis 2017

Zakres stron: 114 - 133

DOI: https://doi.org/10.1515/cait-2017-0045

Słowa kluczowe
endpoint detection, long-term spectral divergence, group delay spectrum

© by Atanas Ouzounov

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

LTSD and GDMD features for Telephone Speech Endpoint Detection

Data publikacji: 30 lis 2017

Zakres stron: 114 - 133

DOI: https://doi.org/10.1515/cait-2017-0045

Słowa kluczoweendpoint detection, long-term spectral divergence, group delay spectrum

© by Atanas Ouzounov

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Słowa kluczowe
endpoint detection, long-term spectral divergence, group delay spectrum