Robust speaker identification based on selective use of feature vectors
In: Pattern recognition letters, Jg. 28 (2007), Heft 1, S. 85-89
academicJournal
- print, 7 ref
Zugriff:
A new method for speaker identification that selectively uses feature vectors for robust decision-making is described. Experimental results, with short speech segments ranging from 0.25 to 2 s, showed that our method consistently outperforms other approaches yielding relative improvements of 20-51% and 15-30% over baseline GMM and the LDA-GMM systems, respectively.
Titel: |
Robust speaker identification based on selective use of feature vectors
|
---|---|
Autor/in / Beteiligte Person: | KWON, Soonil ; NARAYANAN, Shrikanth |
Link: | |
Zeitschrift: | Pattern recognition letters, Jg. 28 (2007), Heft 1, S. 85-89 |
Veröffentlichung: | Amsterdam: Elsevier, 2007 |
Medientyp: | academicJournal |
Umfang: | print, 7 ref |
ISSN: | 0167-8655 (print) |
Schlagwort: |
|
Sonstiges: |
|