Main / Shopping / Tidigits
File size: 973mb
Philadelphia: Linguistic Data Consortium, This corpus contains speech which was originally designed and collected at Texas Instruments, Inc. (TI) for the purpose of designing and evaluating algorithms for speaker-independent recognition of connected digit sequences.
A SPEAKER-INDEPENDENT CONNECTED-DIGIT DATABASE. R. Gary Leonard and George R. Doddington. Texas Instruments Incorporated Central Research. TIDIGITS is a comparatively simple connected digits recognition task. Like for many well-known corpora, Kaldi includes a example script for it.
It is fairly typical for. The TIDIGITS database consists of men, women, boys and girls reading digit strings of varying lengths; these are sampled at 20 kHz. It's available from the LDC. The spoken digits are from the TIDIGITS corpus of several thousand continuous digits utterances, which also include isolated digits for each of.
For this lab, we'll be following the Kaldi tutorial for building TIDIGITS. The lab will utilize a virtual machine for the VirtualBox host that contains. They're not free. You have to purchase them from the Linguistic Data Consortium, waybuchmagi.website Note that you almost certainly.
Are there any accuracy (WER) studies done on pocketsphinx on TIDIGITS on any other similar reference database? Are those numbers. Here you can find old models previously used for various evaluations. They are provided mostly for historic reasons. Most of them are built in CMU from LDC.
The database is “TIDIGITS”-- very old, very easy task, clean recording, people saying digits. (connected digits, i.e. without pauses). Train and test sets each have.