𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Temporal control improvement of hidden Markov models for automatic speech recognition

✍ Scribed by Christine Dours-Senac

Book ID
107910406
Publisher
Elsevier Science
Year
1991
Weight
778 KB
Volume
32
Category
Article
ISSN
0165-6074

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Continuously variable duration hidden Ma
Continuously variable duration hidden Markov models for automatic speech recognition
✍ S.E. Levinson πŸ“‚ Article πŸ“… 1986 πŸ› Elsevier Science 🌐 English βš– 655 KB

During tile past decade, the applicability of hidden Markov models (HMM) to various facets of speech analysi s has been demonstrated in several different experiments. These investigations all rest on the assumption that speech is a quasi-stationary process whose stationary intervals can be identifie

Large scale discriminative training of h
Large scale discriminative training of hidden Markov models for speech recognition
✍ P.C. Woodland; D. Povey πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 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

A Markov model acoustic phonetic compone
A Markov model acoustic phonetic component for automatic speech recognition †
✍ C.C. Tappert πŸ“‚ Article πŸ“… 1977 πŸ› Elsevier Science βš– 794 KB

A Markov-model acoustic-phonetic component is constructed for the synthesis of standard acoustic representations of connected speech. The primary building blocks are phones with Markov models structured so that phone length, spectral power and fundamental frequency are parametrically controlled. The