Comparison of Voice Activity Detection algorithms for VoIP

被引:43
作者
Prasad, RV [1 ]
Sangwan, A [1 ]
Jamadagni, HS [1 ]
Chiranth, MC [1 ]
Sah, R [1 ]
Gaurav, V [1 ]
机构
[1] Indian Inst Sci, CEDT, Bangalore 560012, Karnataka, India
来源
ISCC 2002: SEVENTH INTERNATIONAL SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, PROCEEDINGS | 2002年
关键词
D O I
10.1109/ISCC.2002.1021726
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We discuss techniques for Voice Activity Detection (VAD) for Voice over Internet Protocol (VoIP). VAD aids in saving bandwidth requirement of a voice session thereby increasing the bandwidth efficiently. In this paper, we compare the quality of speech, level of compression and computational complexity for three time-domain and three frequency-domain VAD algorithms. Implementation of time-domain algorithms is computationally simple. However, better speech quality is obtained with the frequency-domain algorithms. A comparison of merits and demerits along with the subjective quality, of speech after removal of silence periods is presented for all the algorithms. A quantitative measurement of speech quality for different algorithms is also presented.
引用
收藏
页码:530 / 535
页数:6
相关论文
共 13 条
  • [1] [Anonymous], WIRELESS DIGITAL COM
  • [2] CHO YD, 2001, IEEE ELECT LETT 0206
  • [3] ELMALEH K, 1997, IEEE CAN C EL COMP E, P470
  • [4] FLOOD JE, TELECOMMUNICATIONS S
  • [5] Gold B., SPEECH AUDIO SIGNAL
  • [6] Pollak P., 1993, EUROSPEECH, V93, P1073
  • [7] POLLAK P, 1995, P IEEE WORKSH NONL S, P388
  • [8] Pracht S., 2001, CISCOWORLD MAGAZINE
  • [9] RABINER LR, 1975, BELL TECHNICAL J FEB, P297
  • [10] *RTP, 1889 RTP RFC