ASR emotional speech: Clarifying the issues and enhancing performance

T. Athanaselis, S. Bakamidis, I. Dologlou, Roddy Cowie, Ellen Douglas-Cowie, C. Cox

Research output: Contribution to journalArticle

59 Citations (Scopus)

Abstract

There are multiple reasons to expect that recognising the verbal content of emotional speech will be a difficult problem, and recognition rates reported in the literature are in fact low. Including information about prosody improves recognition rate for emotions simulated by actors, but its relevance to the freer patterns of spontaneous speech is unproven. This paper shows that recognition rate for spontaneous emotionally coloured speech can be improved by using a language model based on increased representation of emotional utterances. The models are derived by adapting an already existing corpus, the British National Corpus (BNC). An emotional lexicon is used to identify emotionally coloured words, and sentences containing these words are recombined with the BNC to form a corpus with a raised proportion of emotional material. Using a language model based on that technique improves recognition rate by about 20%. (c) 2005 Elsevier Ltd. All rights reserved.
Original languageEnglish
Pages (from-to)437-444
Number of pages8
JournalNeural Networks
Volume18
Issue number4
DOIs
Publication statusPublished - May 2005

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

Fingerprint Dive into the research topics of 'ASR emotional speech: Clarifying the issues and enhancing performance'. Together they form a unique fingerprint.

Cite this