42 search results - page 1 / 9 » Improved speaker recognition when using i-vectors from multi... |
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
The concept of speaker recognition using i-vectors was recently introduced offering state-of-the-art performance. An i-vector is a compact representation of a speaker’s utteranc...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
The recently developed i-vector framework for speaker recognition has set a new performance standard in the research field. An i-vector is a compact representation of a speaker u...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
The SRI speaker recognition system for the 2010 NIST speaker recognition evaluation (SRE) incorporates multiple subsystems with a variety of features and modeling techniques. We d...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
We propose Cross-Channel Spectral Subtraction (CCSS), a source separation method for recognizing meeting speech where one microphone is prepared for each speaker. The method quick...
ICASSP
2008
IEEE
13 years 11 months ago
2008
IEEE
This paper describes an algorithm that performs a simple form of computational auditory scene analysis to separate multiple speech signals from one another on the basis of the mod...