VAD techniques for real-time speech transmission on the Internet

A. Sangwan1, M.C. Chiranth2, H.S. Jamadagni3, R. Sah1, R. Venkatesha Prasad3, V. Gaurav1
1Department of Electronics & Communication, PESIT, UK
2Department of Electronics & Communication, PESIT
3IISc, Design Technology, Bangalore, India

Tóm tắt

We discuss techniques for voice activity detection (VAD) for voice over Internet Protocol (VoIP). VAD aids in reducing the bandwidth requirement of a voice session, thereby using bandwidth efficiently. Such a scheme would be implemented in the application layer. Thus the VAD is independent of the lower layers in the network stack (see Flood, J.E., "Telecommunications Switching - Traffic and Networks", Prentice Hall India). We compare four time-domain VAD algorithms in terms of speech quality, compression level and computational complexity. A comparison of the relative merits and demerits along with the subjective quality of speech after the pruning of silence periods is presented for all the algorithms. A quantitative measurement of speech quality for different algorithms is also presented.

Từ khóa

#Speech #Internet #Payloads #Bandwidth #Telephony #Throughput #Protocols #Computational complexity #Background noise #Electronic mail

Tài liệu tham khảo

haykin, 0, An Introduction to Analog &amp Digital Communications, 202 0, Tanenbaum Computer Networks prasad, 2002, Comparison of Voice Activity Detection Algorithms for VoIP, submitted to the Seventh IEEE Symposium on Computers and Communication xie, 0, Enhancing VoIP designs with PCM Coders, Communication System Design Magazine cho, 2001, Mixed Decision-Based Noise Adaption for Speech Enhancement, Electron Lett Online, 10.1049/el:20010368 sohn, 1999, A statistical model-based voice activity detection, IEEE Signal Processing Letters, 6 flood, 0, Telecommunication Switching Traffic and Networks 10.1109/CCECE.1997.608260 feher, 2001, Wireless Digital Communications pollak, 1993, Noise Suppression System for a Car, Proceedings of the Third European Conference on Speech Communication and Technology Eurospeech '93, 1073 10.1002/j.1538-7305.1975.tb02840.x 10.1002/9781118142882 sangwan, 2001, Voice Activity Detection for VoIP- Time and Frequency domain Solutions, Proc Tenth Annual Symposium on Multimedia Communication and Signal Processing, 20 0, RTP Real Time Protocol RFC 1889