Detail publikace

Automatic Vocal Effort Detection for Reliable Speech Recognition

ZELINKA, P. SIGMUND, M.

Originální název

Automatic Vocal Effort Detection for Reliable Speech Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

This paper describes an approach for enhancing the robustness of isolated words recognizer by extending its flexibility in the domain of speaker's variable vocal effort level. An analysis of spectral properties of spoken vowels in four various speaking modes (whispering, soft, normal, and loud) confirm consistent spectral tilt changes. Severe impact of vocal effort variability on the accuracy of a speaker-dependent word recognizer is presented and an efficient remedial measure using multiple-model framework paired with accurate speech mode detector is proposed.

Klíčová slova

vocal effort detection, speech recognition, hidden Markov models

Autoři

ZELINKA, P.; SIGMUND, M.

Rok RIV

2010

Vydáno

1. 9. 2010

Místo

Kittilä

ISBN

978-1-4244-7876-7

Kniha

Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010)

Strany od

349

Strany do

354

Strany počet

6

BibTex

@inproceedings{BUT35916,
  author="Petr {Zelinka} and Milan {Sigmund}",
  title="Automatic Vocal Effort Detection for Reliable Speech Recognition",
  booktitle="Proceedings of the 2010 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2010)",
  year="2010",
  pages="349--354",
  address="Kittilä",
  isbn="978-1-4244-7876-7"
}