The segmentation of uttered speech into phonetic units is a key processing task for successfully implementing speech recognition systems. This paper presents a smart approach to phonetic segmentation of uttered speech that separates vowels from consonants. Time-domain feature-extraction algorithms are applied to speech to extract features at minimum computational cost. Fuzzy decision logic is used to infer the effective separation point, considering coarticulations specific to uttered speech. Experimental results have shown this approach to be effective in separating phonetic units, while requiring minimal computing power and reducing system complexity.

Using fuzzy logic and features measured from the time domain to achieve smart separation of phonetic units / M. Malcangi - In: Latest trends on communications : 14th WSEAS International Conference on COMMUNICATIONS, Corfu Island, Greece, July 23-25, 2010 / [a cura di] N. E. Mastorakis, V. Mladenov, Z. Bojkovic. - Stevens Point, USA : WSEAS Press, 2010. - ISBN 9789604742004. - pp. 248-251 (( Intervento presentato al 14th. convegno WSEAS International Conference on Communications tenutosi a Corfu Island, Greece nel 2010.

Using fuzzy logic and features measured from the time domain to achieve smart separation of phonetic units

M. Malcangi
Primo
2010

Abstract

The segmentation of uttered speech into phonetic units is a key processing task for successfully implementing speech recognition systems. This paper presents a smart approach to phonetic segmentation of uttered speech that separates vowels from consonants. Time-domain feature-extraction algorithms are applied to speech to extract features at minimum computational cost. Fuzzy decision logic is used to infer the effective separation point, considering coarticulations specific to uttered speech. Experimental results have shown this approach to be effective in separating phonetic units, while requiring minimal computing power and reducing system complexity.
Fuzzy decision logic; Pitch estimation; Speech analysis; Speech energy; Speech recognition; Speech segmentation; Zero-crossing rate
Settore INF/01 - Informatica
2010
Book Part (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/146241
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
social impact