Title | ||
---|---|---|
Speech recognition experiments with the SPEECON database using several robust front-ends |
Abstract | ||
---|---|---|
Abstract In this paper we deal ,with the robustness problem ,in speech recognition, using a Spanish subset of the recently collected SPEECON database, and focusing on the front-end side of the recognizer. Cross-microphoneand,cross-environment recogni- tion tests are presented ,using both read and ,spontaneous continuous speech utterances. Our semi-continuous sub-word HMM back-end was fixed for all the tests. For comparison, we used both the clean-speech and the noisy-speech cepstrum- based ETSI standard front-ends, as well as a few relatively simple variants of the ,front-end that ,is based ,on frequency- filtering (FF) features. In all our tests, the best word error rates scores were obtained with the FF front-end. Moreover, a technique based on a,long-term log spectral mean,subtraction was successfully used to reduce the reverberation affecting the utterances from the furthest microphones. |
Year | Venue | Keywords |
---|---|---|
2004 | INTERSPEECH | front end,word error rate,speech recognition |
Field | DocType | Citations |
Pattern recognition,Voice activity detection,Computer science,Word error rate,Speech recognition,Natural language processing,Artificial intelligence,VoxForge | Conference | 1 |
PageRank | References | Authors |
0.35 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pere Pujol | 1 | 12 | 1.32 |
Jaume Padrell | 2 | 23 | 4.95 |
Climent Nadeu | 3 | 611 | 60.16 |
Dusan Macho | 4 | 47 | 6.58 |