IMPROVED VOICE ACTIVITY DETECTOR

摘要

The present invention relates to a voice activity detector (VAD) (20; 30) comprising at least a first primary voice detector (23; 33a). The voice activity detector (20; 30 is configured to output a speech decision "vad_flag" indicative of the presence of speech in an input signal based on at least a primary speech decision "vad_prim_A" produced by said first primary voice detector (23; 33a). The voice activity detector (20; 30) further comprises a short term activity detector (26; 36) and the voice activity detector (20; 30) is further configured to produce a music decision "vad_music" indicative of the presence of music in the input signal based on a short term primary activity signal avad_act_prim_A" produced by said short term activity detector (26; 36) based on the primary speech decision "vad_prim_A" produced by the first voice detector (23, 33a). The short term primary activity signal "vad_act_prim_A" is proportional to the presence of music in the input signal. The invention also relates to a node, e.g. a terminal, in a communication system comprising such a VAD.