Impact of acoustical voice activity detection on spontaneous filled pause classification

Citation

Hamzah, Raseeda and Jamil, Nursuriati and Seman, Noraini and Ardi, Norizah and C. Doraisamy, Shyamala (2014) Impact of acoustical voice activity detection on spontaneous filled pause classification. In: 2014 IEEE Conference on Open Systems (ICOS), 26-28 Oct. 2014, Subang Jaya, Selangor, Malaysia. (pp. 1-6).

Abstract

Filled pause detection is imperative for spontaneous speech recognition as it may degrade speech recognition rate. However, filled pause is commonly confused with elongation as they shared the same acoustical properties. Few attempts of classifying filled pause and elongation employed Hidden Markov model. Our proposed method of utilizing Neural Network as a classifier achieved 96% precision rate. We also proved that voice activity detection (VAD) affects the performance of speech recognition. Three acoustical-based VAD are compared and the best precision rate is achieved by incorporating volume and first-order difference features. Experiments are conducted using Malay language spontaneous speeches of Malaysia Parliamentary Debate sessions.

Download File

Preview

PDF (Abstract)
Impact of acoustical voice activity detection on spontaneous filled pause classification.pdf
Download (33kB) | Preview

Additional Metadata

Item Type:	Conference or Workshop Item (Paper)
Divisions:	Faculty of Computer Science and Information Technology
DOI Number:	https://doi.org/10.1109/ICOS.2014.7042400
Publisher:	IEEE
Keywords:	Elongations; Filled pause; Multi-layer perceptron neural network; Voice activity detection
Depositing User:	Nabilah Mustapa
Date Deposited:	31 Jul 2017 05:22
Last Modified:	31 Jul 2017 05:22
Altmetrics:	http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/ICOS.2014.7042400
URI:	http://psasir.upm.edu.my/id/eprint/56314
Statistic Details:	View Download Statistic

Actions (login required)

View Item