论文信息 - A Voice Activity Detection Algorithm for Wireless Communication Systems with Dynamically Varying Background Noise

A Voice Activity Detection Algorithm for Wireless Communication Systems with Dynamically Varying Background Noise

Speech can be modeled as short bursts of vocal energy separated by silence gaps. During typical conversation, talkspurts comprise only 40% of each party’s speech and remaining 60% is silence. Communication systems can achieve spectral gain by disconnecting the users from the spectral resource during silence periods. This letter develops a simple and efficient Voice Activity Detection (VAD) algorithm to work in a mobile environment exhibiting dynamically varying background noise. The VAD uses a classification method involving the full-band energy, ratio of low-band energy to full-band energy, zero-crossing rate, and peakiness measure. key words: voice activity detection, wireless communications

Jae Won Kim | Song In Choi | Byung Sik Yoon | Young Gap You | Min Sik Seo

[1] D. Prezas,et al. Selective modeling of the LPC residual during unvoiced frames: White noise or pulse excitation , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2] H.M. Hafez,et al. Background acoustic noise reduction in mobile telephony , 1986, 36th IEEE Vehicular Technology Conference.

[3] Thomas P. Barnwell,et al. MCCREE AND BARNWELL MIXED EXCITAmON LPC VOCODER MODEL LPC SYNTHESIS FILTER 243 SYNTHESIZED SPEECH-PERIODIC PULSE TRAIN-1 PERIODIC POSITION JITTER PULSE 4 , 2004 .