Publication detail

Impact of vocal effort variability on automatic speech recognition

ZELINKA, P. SIGMUND, M. SCHIMMEL, J.

Original Title

Impact of vocal effort variability on automatic speech recognition

Type

journal article - other

Language

English

Original Abstract

The impact of changes in a speaker's vocal effort on the performance of automatic speech recognition has largely been overlooked by researchers and virtually no speech resources exist for the development and testing of speech recognizers at all vocal effort levels. This study deals with speech properties in the whole range of vocal modes – whispering, soft speech, normal speech, loud speech, and shouting. Fundamental acoustic and phonetic changes are documented. The impact of vocal effort variability on the performance of an isolated-word recognizer is shown and effective means of improving the system's robustness are tested. The proposed multiple model framework approach reaches a 50% relative reduction of word error rate compared to the baseline system. A new specialized speech database, BUT-VE1, is presented, which contains speech recordings of 13 speakers at 5 vocal effort levels with manual phonetic segmentation and sound pressure level calibration.

Keywords

Vocal effort level, robust speech recognition, machine learning

Authors

ZELINKA, P.; SIGMUND, M.; SCHIMMEL, J.

RIV year

2012

Released

5. 7. 2012

Publisher

Elsevier

ISBN

0167-6393

Periodical

Speech Communication

Year of study

54

Number

6

State

Kingdom of the Netherlands

Pages from

732

Pages to

742

Pages count

11

URL

BibTex

@article{BUT88839,
  author="Petr {Zelinka} and Milan {Sigmund} and Jiří {Schimmel}",
  title="Impact of vocal effort variability on automatic speech recognition",
  journal="Speech Communication",
  year="2012",
  volume="54",
  number="6",
  pages="732--742",
  issn="0167-6393",
  url="http://dx.doi.org/10.1016/j.specom.2012.01.002"
}