Sixth European Conference on Speech Communication and Technology
The paralinguistic features, however this conference classifies the “Paralinguistic analysis" as Speaker identification, Keyword/topic spotting, and Language identification, include emotional aspects of voice, which is focused recently on interpersonal communications. Study starts from description and statistics of those features. Among many acoustic characteristics, we investigated features represented in pitch raising and lowering, loudness of speech, and rate of talking; these are not represented in textual meaning of speech that is the content of conventional speech recognition. The paralinguistic features are distinguished from prosodic features, however these two are often confused.
Keywords: paralanguage, prosody, spontaneous speech, transcription
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Kitazawa, S. / Kobayashi, S. (1999): "Paralinguistic features as suprasegmental acoustics observed in natural Japanese dialogue", In EUROSPEECH'99, 33-36.