The traditional approach to automatic speech recognition continues to push the limits of its implementation. The multimodal approach to audio-visual speech recognition and its neuromorphic computational modeling is a novel data driven paradigm that will lead towards zero instruction set computing and will enable proactive capabilities in audio-visual recognition systems. An engineering-oriented deployment of the audio-visual processing framework is discussed in this paper, proposing a bimodal speech recognition framework to process speech utterances and lip reading data, applying soft computing paradigms according to a bio-inspired and the holistic modeling of speech
Bio-inspired audio-visual speech recognition towards the zero instruction set computing / M. Malcangi, H. Quan (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: Engineering Applications of Neural Networks / [a cura di] C. Jayne, L. Iliadis. - Prima edizione. - Switzerland : Springer, 2016. - ISBN 9783319441870. - pp. 326-334 (( Intervento presentato al 17. convegno EANN tenutosi a Aberdeen nel 2016 [10.1007/978-3-319-44188-7_25].
Bio-inspired audio-visual speech recognition towards the zero instruction set computing
M. Malcangi;
2016
Abstract
The traditional approach to automatic speech recognition continues to push the limits of its implementation. The multimodal approach to audio-visual speech recognition and its neuromorphic computational modeling is a novel data driven paradigm that will lead towards zero instruction set computing and will enable proactive capabilities in audio-visual recognition systems. An engineering-oriented deployment of the audio-visual processing framework is discussed in this paper, proposing a bimodal speech recognition framework to process speech utterances and lip reading data, applying soft computing paradigms according to a bio-inspired and the holistic modeling of speechFile | Dimensione | Formato | |
---|---|---|---|
MalcangiQuan_430080_1_En_25_Chapter_Author.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
1.06 MB
Formato
Adobe PDF
|
1.06 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.