HPE IDOL Speech Server produces and uses files with the following file name extensions.
If FFmpeg support is enabled, HPE IDOL Speech Server also accepts a wide range of media file formats when it uses the wav
module to read from files.
AFP
|
Audio Fingerprint feature file |
AM
|
Acoustic model file |
AST
|
Speaker ID classifier set |
ATD
|
Audio template development file |
ATF
|
Audio template file |
ATS
|
Audio template set file |
ATV
|
Audio template feature vector file |
DCT.SZ
|
Pronunciation dictionary file |
DIAG
|
Diagnostics file |
DNN
|
Deep Neural Network acoustic modeling file |
FMD
|
Phoneme time track file |
FXX
|
Audio Fingerprint database index file |
IAN
|
Input acoustic channel normalization file |
IV
|
An iVector file, representing a speaker (audio) template. |
IVP
|
An iVector parameter file, used as input for training, and so on. |
IVD
|
An iVector development file, used in threshold estimation. |
An
|
An iVector set file, containing a set of iVector templates. |
LCF
|
Language classifier file |
LIF
|
Language identification feature file |
LIST
|
List file |
LOG
|
Log file |
NET
|
Phrase search supplementary file |
NET.DPT
|
Phrase search supplementary file |
OTD
|
Obfuscated training data file |
PDT.SZ
|
Word confidence supplementary file |
PGF
|
Pronunciation generation file |
PHI.SZ
|
Acoustic model language key files |
PHN.SZ
|
Acoustic model language key files |
PLM
|
Word confidence supplementary file |
PRB
|
Word confidence supplementary file |
SID
|
Segmenter model file |
SIG
|
Signal processing description file |
SPK
|
Individual speaker ID model file |
SPO
|
Speaker ID optimization file |
SPT
|
Speaker training file |
TKI
|
Audio Fingerprint database index file |
TLM |
Language model file |
TTX
|
Audio Fingerprint database index file |
TXT
|
Text file |
USM
|
Universal Speech Model file |
VOC
|
Vocabulary list file |
WAV
|
WAV audio file |
WDS
|
Valid word list file (supplied in language pack) |
XML
|
XML file |
|