scope:

The GSAD is an independent front-end processing module which can be applied prior to signal processing applications that operate on narrowband or wideband audio input at 10 ms frame length (without lookahead), such as speech or audio codecs. Its primary function is to indicate the input frame activity. For an active frame it further indicates if the input frame is speech or music, and for an inactive frame it indicates whether the frame is a silence frame or an audible noise frame.

This Recommendation is organized as follows. References, definitions, abbreviations/acronyms and conventions are defined in clauses 2, 3, 4 and 5 respectively. Clause 6 gives a general description of the GSAD algorithm including the input sampling rate, the operating frame length, the algorithmic delay, the configurations and the complexity and memory cost. The detailed description of the GSAD algorithm is described in clause 7 where clause 7.1 describes the VAD module and the speech/music discrimination module is described in clause 7.2. Finally in clause 8 the organization of the ANSI C code is described.