๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Hidden Markov model training with contaminated speech material for distant-talking speech recognition

โœ Scribed by Matassoni, Marco (author);Omologo, Maurizio (author);Giuliani, Diego (author);Svaizer, Piergiorgio (author)

Publisher
Academic Press
Year
2002
Tongue
English
Weight
280 KB
Volume
16
Category
Article
ISSN
0885-2308

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

Hidden Markov model training with contam
Hidden Markov model training with contaminated speech material for distant-talking speech recognition
โœ Matassoni, Marco (author);Omologo, Maurizio (author);Giuliani, Diego (author);Sv ๐Ÿ“‚ Article ๐Ÿ“… 2002 ๐Ÿ› Academic Press ๐ŸŒ English โš– 280 KB

A challenging scenario is addressed in which a distant-talking speech recognizer operates in a noisy office environment with model adaptation. The use of a single far microphone as well as that of a microphone array input are investigated. In addition to the benefits from the application of microph

Large scale discriminative training of h
Large scale discriminative training of hidden Markov models for speech recognition
โœ P.C. Woodland; D. Povey ๐Ÿ“‚ Article ๐Ÿ“… 2002 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 197 KB

This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov models (HMMs). This paper concentrates on the maximum mutual information estimation (MMIE) criterion wh

Hidden Markov model-based speech recogni
Hidden Markov model-based speech recognition with intermediate wavelet transform domains
โœ R Singh; K Davis; P V.S Rao ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 633 KB

A discrete wavelet transform algorithm segregates the operand data set sequentially. It generates computational intermediates which represent it at graded resolutions and leads to a reciprocal domain within which information is multiply resolved in terms of the timefrequency localization of the comp

Hidden Markov model representation of qu
Hidden Markov model representation of quantized articulatory features for speech recognition
โœ Kevin Erler; Li Deng ๐Ÿ“‚ Article ๐Ÿ“… 1993 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 707 KB

This paper describes a speech recognizer based on an HMM representation of quantized articulatory features and presents experimental results for its evaluation. Traditional schemes for HMM representation of speech have attempted to model a set of disjoint time segments. In order to create a more rob