Major progress is being recorded regularly on both the technology and exploitation of
automatic speech recognition (ASR) and spoken language systems. However, there are still …

Although much is known about how speech is produced, and research into speech
production has resulted in measured articulatory data, feature systems of different kinds, and …

This chapter provides an accessible introduction for point processes, and especially Hawkes
processes, for modeling discrete, inter-dependent events over continuous time. We start by …

Today's digital contents are inherently multimedia: text, audio, image, video, and so on.
Video, in particular, has become a new way of communication between Internet users with …

To date, there has been limited work in applying Deep Belief Networks (DBNs) for acoustic
modeling in LVCSR tasks, with past work using standard speech features. However, a …

Acoustic Event Detection (AED) aims to identify both timestamps and types of events in an
audio stream. This becomes very challenging when going beyond restricted highlight events …

Incorporating information from the short-time phase spectrum into a feature set for automatic
speech recognition (ASR) may possibly serve to improve recognition accuracy. Currently …

We report on investigations, conducted at the 2006 Johns Hopkins Workshop, into the use of
articulatory features (AFs) for observation and pronunciation models in speech recognition …

Recent years have seen a surge in finding association between faces and voices within a
cross-modal biometric application along with speaker recognition. Inspired from this, we …

Reliable automatic detection of speech/non-speech activity in degraded, noisy audio signals
is a fundamental and challenging task in robust signal processing. As various speech …