Δημοσίευση - ASR for emotional speech: clarifying the issues and enhancing performance

ΑΝΑΖΗΤΗΣΗ

ASR for emotional speech: clarifying the issues and enhancing performance

Ερευνητική περιοχή:  
    
Είδος:  
Άρθρο σε περιοδικό

 

Έτος: 2005
Συγγραφείς: Θεολόγος Αθανασέλης; Στυλιανός Μπακαμίδης; Ιωάννης Δολόγλου; R. Cowie; E. Douglas-Cowie; C. Cox
Περιοδικό: Neural Networks Elsevier Publications
Τόμος: 18
Αριθμός: 4
Σελίδες: 437- 444
Περίληψη:
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%.
[Bibtex]
  • Αποτελέσματα Αναζήτησης