In the past decade, tremendous advances in the state of the art of automatic speech
recognition by machine have taken place. A reduction in the word error rate by more than a …

The authors are concerned with integrating connectionist networks into a hidden Markov
model (HMM) speech recognition system. This is achieved through a statistical interpretation …

Das Thema der vorliegenden Arbeit ist die Problemstellung maschineller Erkennung
gesprochener Sprache. Ein wichtiger Forschungszweig auf diesem Gebiet ist gegenwärtig …

This work involves the analysis of musical instrument sounds, the creation of timbre models,
the estimation of the parameters of the timbre models and the analysis of the timbre model …

The authors present an automatic method for modeling phonological variation using
decision trees. For each phone they construct a decision tree that specifies the acoustic …

In this paper we present two new techniques that have been used to build a large-
vocabulary continuous Hindi speech recognition system. We present a technique for fast …

There will never be sufficient training data to model all the various acoustic-phonetic
phenomena. How to capture important clues and estimate those needed parameters reliably …

As of this writing, the automatic recognition of spontaneous speech by computer is fraught
with errors; many systems transcribe one out of every three to five words incorrectly …

Massive and complex data impose a challenge on the public health community to explore,
analyze, and synthesize valuable information to make timely informed decisions. This study …

In many ways, the lexicon remains the Achilles heel of modern automatic speech
recognizers. Unlike stochastic acoustic and language models that learn the values of their …