Eliminating the negative effect of non-stationary environmental noise is a long-standing
research topic for automatic speech recognition but still remains an important challenge …

New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …

This paper describes a speech recognition system that uses both acoustic and visual
speech information to improve recognition performance in noisy environments. The system …

More recent multimodal systems have moved away from processing simple mouse or
touchpad pointing, and have begun designing systems based on two parallel input streams …

With the growing impact of information technology on daily life, speech is becoming
increasingly important for providing a natural means of communication between humans …

This paper addresses the problem of single channel speech enhancement at very low signal-
to-noise ratios (SNRs)(< 10 dB). The proposed approach is based on the introduction of an …

Human speech perception is robust in the face of a wide variety of distortions, both
experimentally applied and naturally occurring. In these conditions, state-of-the-art …

In speech recognition, confidence measures (CM) are used to evaluate reliability of
recognition results. A good confidence measure can largely benefit speech recognition …

Conversational agents are systems with great potential to enhance human-computer
interaction in industrial settings. Although the number of applications of conversational …

The growing interest in multimodal interface design is inspired in large part by the goals of
supporting more transparent, flexible, efficient, and powerfully expressive means of human …