Detail publikace

TRAPS in Phoneme Classification

MATĚJKA, P.

Originální název

TRAPS in Phoneme Classification

Anglický název

TRAPS in Phoneme Classification

Jazyk

en

Originální abstrakt

This paper deals with several techniques for automatic recognition of unconstrained context-independent phoneme strings. Among the compared techniques, the technique based on TempoRAl Patterns(TRAP) achieves the best results in the clean speech, it achieves about 10% relative improovements against baseline system. Issues such as the optimal length of temporal patterns in the TRAP technique and the effectiveness of mean and variance normalization of the patterns are explored.

Anglický abstrakt

This paper deals with several techniques for automatic recognition of unconstrained context-independent phoneme strings. Among the compared techniques, the technique based on TempoRAl Patterns(TRAP) achieves the best results in the clean speech, it achieves about 10% relative improovements against baseline system. Issues such as the optimal length of temporal patterns in the TRAP technique and the effectiveness of mean and variance normalization of the patterns are explored.

Dokumenty

BibTex


@inproceedings{BUT10752,
  author="Pavel {Matějka}",
  title="TRAPS in Phoneme Classification",
  annote="This paper deals with several techniques for automatic recognition of unconstrained context-independent phoneme strings. Among the compared techniques, the technique based on TempoRAl Patterns(TRAP) achieves the best results in the clean speech, it achieves about 10% relative improovements against baseline system. Issues such as the optimal length of temporal patterns in the TRAP technique and the effectiveness of mean and variance normalization of the patterns are explored.",
  address="FEKT VUT v Brně",
  booktitle="Proc. of 9th Conference and Competition Student EEICT 2003",
  chapter="10752",
  institution="FEKT VUT v Brně",
  year="2003",
  month="april",
  pages="640",
  publisher="FEKT VUT v Brně",
  type="conference paper"
}