Publication Details
QUALCOMM-ICSI-OGI Features for ASR
Dupont Stephane, Msc (ICSI Berkeley)
Garudadri Harinath, Mcs. (Qualcomm)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Heřmanský Hynek, prof. Ing., Dr.Eng. (DCGM FIT BUT)
Jain Pratibha, Msc. (OGI)
Kajarekar Sachin, Ph.D. (SRI)
Morgan Nelson, Prof. (ICSI Berkeley)
feature extraction, distributed speech recognition, Aurora task, RASTA, TRAP
Feature extraction module for the Aurora task based on a combination of a Wiener filtering with linear discriminant RASTA filtering and nonlinear tempoRAl Pattern (TRAP) classifier.
Our feature extraction module for the Aurora task is based on a combination of a conventional noise supression technique (Wiener filtering) with our temporal processing technigues (linear discriminant RASTA filtering and nonlinear TempoRAl Pattern (TRAP) classifier). We observe better than 58% relative error improvement on the prescribed Aurora Digit Task, a performance level that is somewhat better than the new ETSI Advanced Feature standard. Furthermore, to test generalization of our approach to an independent test set not available during development, we evaluate performance on American English SpeechDatCar digits and show 10.54% relative improvement over the new ETSI standard.
@INPROCEEDINGS{FITPUB7073, author = "Luk\'{a}\v{s} Burget and Stephane Dupont and Harinath Garudadri and Franti\v{s}ek Gr\'{e}zl and Hynek He\v{r}mansk\'{y} and Pratibha Jain and Sachin Kajarekar and Nelson Morgan", title = "QUALCOMM-ICSI-OGI Features for ASR", pages = 4, booktitle = "Proc. 7th International Conference on Spoken Language Processing", year = 2002, location = "Denver, US", publisher = "International Speech Communication Association", ISBN = "1-876346-42-6", language = "english", url = "https://www.fit.vut.cz/research/publication/7073" }