Pinned Repositories
abdelkbir
Speech Recognition with HHM
Calculate-SNR-SDR
Script to calculate SNR and SDR using python
SDDN-DATABASE
The SDDN database are based on the Speech commands dataset . we relied only on some audio files of the spoken digits from this database for different speakers in terms of age, sex, and accent. The SDDN consists of ten files from zero to nine, every file contains five subfiles of noise (Babble, cafe, Pedestrian area, street, pink) every subfile contains five subfiles that consist SNR levels (- 10 dB,-5 dB, 0 dB, 5 dB, 10 dB). The final SDNN dataset consisted of 375000 utterances of 10 words broken into the noises files and SNR Levels, (10 digits , numbers of utterances is 1500 for every digit , numbers of noise is 5 in 5 SNR levels: 10,5,5 1500, 375000 ) .The 375000 wave audio files of people saying then different digits. The archive is over 12GB. more detail https://ieeexplore.ieee.org/document/8723698/authors#authors by A. Ouisaadane Department of Mathematics and Computer Science, Polydisciplinary Faculty, Sultan Moulay Slimane University, Benimellal, Morocco S. Safi Department of Mathematics and Computer Science, Polydisciplinary Faculty, Sultan Moulay Slimane University, Benimellal, Morocco M. Frikel GREYC Laboratory, ENSICAEN School, LAC Laboratory, Caen-Normandie University, Caen, France
abdowiss's Repositories
abdowiss doesn’t have any repository yet.