The performance levels of most current speech recognizers degrade significantly when
environmental noise occurs during use. Such performance degradation is mainly caused by …

Voice conversion, as considered in this paper, is defined as modifying the speech signal of
one speaker (source speaker) so that it sounds as if it had been pronounced by a different …

The objective of voice conversion algorithms is to modify the speech by a particular source
speaker so that it sounds as if spoken by a different target speaker. Current conversion …

Voice conversion is defined as modifying the speech signal of one speaker (source speaker)
so that it sounds as if it had been pronounced by a different speaker (target speaker). This …

Robust speech systems in mobile environment have gained a special interest in recent
years in order to enable access to remote voice-activated services. In this context, three …

We present a stochastic mapping technique for robust speech recognition that uses stereo
data. The idea is based on constructing a Gaussian mixture model for the joint distribution of …

To improve recognition performance in noisy environments, multicondition training is usually
applied in which speech signals corrupted by a variety of noise are used in acoustic model …

The paper compares, on a database recorded in a car, a number of signal analysis and
speech enhancement techniques as well as some approaches to adapt speech recognition …

We propose a new framework and the associated maximum-likelihood and discriminative
training algorithms for the variable-parameter hidden Markov model (VPHMM) whose mean …

In real-life applications, errors in the speech recognition system are mainly due to inefficient
detection of speech segments, unreliable rejection of Out-Of-Vocabulary (OOV) words, and …