INVESTIGADORES
FERRER Luciana
congresos y reuniones científicas
Título:
Effects of audio and ASR quality on cepstral and high-level speaker verification systems
Autor/es:
A. STOLCKE; M. GRACIARENA; L. FERRER
Reunión:
Workshop; Proc. Odyssey Speaker and Language Recognition Workshop; 2012
Institución organizadora:
International Speech Communication Association
Resumen:
Speech data for NIST speaker recognition evaluations has
traditionally been distributed in compressed, telephone
quality form, even for microphone data that was originally recorded at higher quality. We evaluate the effect
that improved audio quality has for speaker verification
performance, using a recently released full-bandwidth
version of microphone data from the SRE2010 evaluation. Remarkably, we find substantially improved results
even though the underlying speaker recognition models
remain based on a telephone-band feature front end. For
a cepstral GMM system we show improvements purely
from the elimination of lossy (mu-law) coding and more effective noise reduction filtering at the full bandwidth. We
also find that higher-level speaker recognition systems
can benefit from better ASR quality enabled by the improved audio quality. Specifically, we show that a speech
recognizer trained on full-bandwidth, distant-microphone
meeting speech data yields reduced speaker verification
error for speaker models based on MLLR features and
word-N-gram features.