Voice Activity Detection in Noisy Environments Based on Double-Combined Fourier Transform and Line Fitting
Authors:
Open Access
- 6 August 2014
- journal article
- research article
- Published by Hindawi Limited in The Scientific World Journal
- Vol. 2014, 1-12
Abstract
A new voice activity detector for noisy environments is proposed. In conventional algorithms, the endpoint of speech is found by applying an edge detection filter that finds the abrupt changing point in a feature domain. However, since the frame energy feature is unstable in noisy environments, it is difficult to accurately find the endpoint of speech. Therefore, a novel feature extraction algorithm based on the double-combined Fourier transform and envelope line fitting is proposed. It is combined with an edge detection filter for effective detection of endpoints. Effectiveness of the proposed algorithm is evaluated and compared to other VAD algorithms using two different databases, which are AURORA 2.0 database and SITEC database. Experimental results show that the proposed algorithm performs well under a variety of noisy conditions.Keywords
Funding Information
- Seoul R&BD Program (WR080951)
This publication has 15 references indexed in Scilit:
- Jointly Gaussian PDF-Based Likelihood Ratio Test for Voice Activity DetectionIEEE Transactions on Audio, Speech, and Language Processing, 2008
- Dual Channel Based Speech Enhancement Using Novelty Filter for Robust Speech Recognition in Automobile EnvironmentIEEE Transactions on Consumer Electronics, 2006
- Voice activity detection based on multiple statistical modelsIEEE Transactions on Signal Processing, 2006
- Statistical voice activity detection using a multiple observation likelihood ratio testIEEE Signal Processing Letters, 2005
- Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environmentsIEEE Transactions on Speech and Audio Processing, 2005
- Efficient voice activity detection algorithms using long-term speech informationSpeech Communication, 2004
- Spectral Subtraction Using Spectral Harmonics for Robust Speech Recognition in Car Environments2003
- Wavelet speech enhancement based on the Teager energy operatorIEEE Signal Processing Letters, 2001
- A statistical model-based voice activity detectionIEEE Signal Processing Letters, 1999
- Application of hidden Markov models to automatic speech endpoint detectionComputer Speech & Language, 1987