AMIRAL: A Block-Segmental Multirecognizer Architecture for Automatic Speaker Recognition
✍ Scribed by Corinne Fredouille; Jean-François Bonastre; Teva Merlin
- Publisher
- Elsevier Science
- Year
- 2000
- Tongue
- English
- Weight
- 323 KB
- Volume
- 10
- Category
- Article
- ISSN
- 1051-2004
No coin nor oath required. For personal study only.
✦ Synopsis
In the wide domain of automatic speech recognition, extracting the relevant information carried by the speech signal is far from easy. Diversity, redundancy, and variability, the main characteristics of the speech signal, make this task particularly difficult. The work reported here presents a multirecognizer architecture designed to cope with this issue in the framework of Automatic Speaker Recognition. This architecture, based on various individual recognizers, exploits different classes of information conveyed by the speech signal. In this paper, two classes of information are investigated: information related to the frequency domain, and "dynamic" information. This multirecognizer architecture is coupled with a blocksegmental approach applied on each classifier. The overall system allows us to emphasize the most informative temporal blocks and to discard the least informative ones or those corrupted by noise. The AMIRAL system developed by the LIA integrates both approaches and was tested during the NIST/NSA 1999 speaker recognition evaluations. The results of these experiments for the tasks of Speaker Verification ("One Speaker" and "Two Speakers") and Speaker Tracking are provided and discussed.