Project DITELO

ITC  Trento, ItalyPhoto

Daniele Falavigna, born in Verona (Italy) in 1960. Laurea degree in Electronic Engeneering in 1985,  from University of Padova. Joined IRST in 1988, working in the Speech Recognition Group. In the past, involved in research on: acoustic modeling of speech, automatic speech segmentation and labeling, speaker identification and verification. Current interests are: speech analysis, acoustic modeling for speech recognition and software architectures for speech recognition.



Research topics


Speaker Identification and Verification;

Telephone Speech Recognition;

Automatic Speech Segmentation and Labeling;

Recent publications

  A. Facco, D. Falavigna, R. Gretter, M. Vigano` "Design and Evaluation of Acoustic and Language Models for Large Scale Telephone Services".  Speech Communication, vol. 48, no. 2, May 2006.

  D. Falavigna, R. Gretter, D. Seppi, G. Stemmer "Word Duration Modeling for Word Graph Rescoring in LVCSR".  Proceedings of Interspeech, pp. 1805-1808, Antwerp (B), August 2007.

  D. Falavigna, et al. "The Irst English-Spanish Translation System for European Parliament Speeches".  Proceedings of Interspeech, pp. 2833-2836, Antwerp (B), August 2007.
Daniele Falavigna
Via Sommarive
38050 Povo (Trento) - Italy

phone:          (+39) 461-314.562
fax:               (+39) 461-314.591
secretary:   (+39) 461-314.592