Automatic speaker identification
Contact person
Ivan MAGRIN-CHAGNOLLEAU
Scientific framework and objectives
The aim of automatic speaker identification is to determine the identity of a speaker from a recorded utterance, or to verify a proposed identity for a given utterance, i.e., accepting or rejecting it.
Read more...
The researcher's aim is to obtain speaker models; they are most of the time based on cepstral analysis and Gaussian mixture modelling.
Financial support
- EVALDA-ALIZE
MENRT 2003-2005
Publications
- Magrin-Chagnolleau, I., Durou, G., Bimbot, F., 2002, "Application of Time-Frequency Principal Component Analysis to Text-Independent Speaker Identification", IEEE Transactions on Speech and Audio Processing, 10, pp. 371-378
- Meignier, S., Bonastre, J.F., Magrin-Chagnolleau, I., 2002, "Speaker Utterances tying among speaker segmented audio documents using hierarchical classification: towards speaker indexing of audio databases", proc. of ICSLP 2002, Denver, USA, September 2002, ISCA, pp. 577-580
- Moraru, D., Meignier, S., Besacier, L., Bonastre, J.F., Magrin-Chagnolleau, I., 2003, "The ELISA consortium Approaches in Speaker Segmentation during the NIST 2002 Speaker Recognition Evaluation", proc. of IEEE ICASSP 2003, Hong-Kong, April 2003, IEEE, pp. 4
|