Content for TS 26.177 Word version: 17.0.0
The present document specifies the digital test sequences for the DSR Extended Advanced Front-end speech codec. These sequences can be used to test for a bit exact implementation of the DSR Advanced Front-end codec and quantization (TS 26.243
The following documents contain provisions, which through reference in this text, constitute provisions of the present document.
References are either specific (identified by date of publication, edition number, version number, etc.) or non-specific.
For a specific reference, subsequent revisions do not apply.
For a non-specific reference, the latest version applies. In the case of a reference to a 3GPP document (including a GSM document), a non-specific reference implicitly refers to the latest version of that document in the same Release as the present document.
: "ANSI-C code for the Fixed-Point Distributed Speech Recognition Extended Advanced Front-end".
ETSI ES 202 050 (2007-01) V1.1.5: "Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Advanced front-end feature extraction algorithm; Compression algorithms DSR advanced front end."
ETSI ES 202 212 (2005-11) V1.1.2: "Speech Processing, Transmission and Quality Aspects (STQ); Distributed speech recognition; Extended advanced front-end feature extraction algorithm; Compression algorithms; Back-end speech reconstruction algorithm".
: "Adaptive Multi-Rate (AMR) Wideband speech codec test sequences"
For the purposes of the present document, the following abbreviations apply:
Distributed Speech Recognition
European Telecommunications Standards Institute
Global System for Mobile communications
Speech Enabled Services
Voice Activity Detector
eXtended Advanced Front-end
Digital test sequences are provided to test for a bit exact implementation of the Distributed Speech Recognition Extended Advanced Front-end (TS 26.243
The test sequences may also be used to verify installations of the ANSI C code in TS 26.243
Clause 5 describes the format of the files, which contain the digital test sequences.
This clause provides information on the format of the digital test sequences for the DSR Extended Advanced Front-end (TS 26.243
The test sequence files in PC (little-endian) byte order are provided in archive files (ZIP format), which accompany the present document.
Following decompression, three types of file are provided:
*.inp - Input to the speech encoder.
*.cep - Cepstral output of the encoder, input to the quantizer.
*.pitch - Pitch output of the encoder, input to the quantizer.
*.class - Class output of the encoder, input to the quantizer.
*.vad - VAD output of the encoder, input to the quantizer.
*.bs - Output of the quantizer
Two test scripts are provided for exercising the Extended Advanced Front-end and quantizer functions.
All file formats are described in TS 26.243
Forty-three encoder input sequences are provided, 22 with 8kHz sampling, 23 with 16kHz sampling.
T00.INP - T21.INP as described in the AMR test sequences document TS 26.074.
T00.INP - T22.INP as described in the AMR WB test sequences document TS 26.174.