Miranda, E. R. Automatic Sound Identification based on Prosodic Listening. Proceedings of 17th International Congress on Acoustics, September 2001 Universita di Roma La Sapienza

Sony CSL authors: Eduardo Miranda

Abstract

This paper presents a system for the identification of vocal and vocal-like sounds by means of a classificatory scheme based upon their prosodic attributes (European Patent No. 01400821.3-2218). The system firstly segments examples of the sound classes in question and performs a number of analyses on these segments in order to determine their prosodic attributes. Then, it builds a classificatory scheme, which will be used to identify an unknown sound. For example, consider the identification of the language of utterances spoken in English, French and Japanse. In this case, the system establishes a classificatory scheme from samples of speech in these three languages. Then, the system infers the language of unknown utterances by matching their prosodic information with the classificatory scheme. The system is not, however, limited to language identification tasks; it can also identify singing styles and a number of animal calls. Given the appropriate training data, the system is able to identify such sounds with great accuracy.

Keywords: speech, prosody, perception, analysis, sound identification, language identificaion, music, Artificial Intelligence

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@INPROCEEDINGS { miranda:01e, AUTHOR="Miranda, E. R.", BOOKTITLE="Proceedings of 17th International Congress on Acoustics", MONTH="September", ORGANIZATION="Universita di Roma La Sapienza", TITLE="Automatic Sound Identification based on Prosodic Listening", YEAR="2001", }