Evaluating the intelligibility benefit of speech modifications in known noise conditions

Martin Cooke, Catherine Mayo, Cassia Valentini-Botinhao, Yannis Stylianou, Bastian Sauert, Yan Tang

Research output: Contribution to journalArticlepeer-review

Abstract

The use of live and recorded speech is widespread in applications where correct message reception is important. Furthermore, the deployment of synthetic speech in such applications is growing. Modifications to natural and synthetic speech have therefore been proposed which aim at improving intelligibility in noise. The current study compares the benefits of speech modification algorithms in a large-scale speech intelligibility evaluation and quantifies the equivalent intensity change, defined as the amount in decibels that unmodified speech would need to be adjusted by in order to achieve the same intelligibility as modified speech. Listeners identified keywords in phonetically-balanced sentences representing ten different types of speech: plain and Lombard speech, five types of modified speech, and three forms of synthetic speech. Sentences were masked by either a stationary or a competing speech masker. Modification methods varied in the manner and degree to which they exploited estimates of the masking noise. The best-performing modifications led to equivalent intensity changes of around 5 dB in moderate and high noise levels for the stationary masker, and 3-4 dB in the presence of competing speech. These gains exceed those produced by Lombard speech. Synthetic speech in noise was always less intelligible than plain natural speech, but modified synthetic speech reduced this deficit by a significant amount.

Original languageEnglish (US)
Pages (from-to)572-585
Number of pages14
JournalSpeech Communication
Volume55
Issue number4
DOIs
StatePublished - May 1 2013
Externally publishedYes

Keywords

  • Speech intelligibility
  • Speech modification
  • Synthetic speech

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Modeling and Simulation
  • Communication
  • Linguistics and Language
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Evaluating the intelligibility benefit of speech modifications in known noise conditions'. Together they form a unique fingerprint.

Cite this