Event detection is a fundamental yet critical component in automatic speech recognition (ASR) systems that attempt to extract knowledge-based features at the front-end level. In this context, it is common practice to design the detectors inside well-known frameworks based on artificial neural network (ANN) or support vector machine (SVM). In the case of ANN, speech scientists often design their detector architecture relying on conventional feed-forward multi-layer perceptron (MLP) with sigmoidal activation function. The aim of this paper is to introduce other ANN architectures inside the context of detection-based ASR. In particular, a bank of feed-forward MLPs using sinusoidal activation functions is set up to address the event detection problem. Experimental results demonstrate the effectiveness of this ANN design for speech attribute detectors.

SINISCALCHI, S.M., CLEMENTS, M.A., GENTILE, A., VASSALLO, G., SORBELLO, F. (2006). A Study of Perceptron Mapping Capability to Design Speech Event Detectors. In Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on. (pp.805-808). IEEE.

A Study of Perceptron Mapping Capability to Design Speech Event Detectors

SINISCALCHI, Sabato Marco;GENTILE, Antonio;VASSALLO, Giorgio;SORBELLO, Filippo
2006-01-01

Abstract

Event detection is a fundamental yet critical component in automatic speech recognition (ASR) systems that attempt to extract knowledge-based features at the front-end level. In this context, it is common practice to design the detectors inside well-known frameworks based on artificial neural network (ANN) or support vector machine (SVM). In the case of ANN, speech scientists often design their detector architecture relying on conventional feed-forward multi-layer perceptron (MLP) with sigmoidal activation function. The aim of this paper is to introduce other ANN architectures inside the context of detection-based ASR. In particular, a bank of feed-forward MLPs using sinusoidal activation functions is set up to address the event detection problem. Experimental results demonstrate the effectiveness of this ANN design for speech attribute detectors.
IEEE International Conference on Acoustic, Speech and Signal Processing, ICASPP 2006
Tolosa Francia
Maggio 2006
2006
4
ISSN 1520-6149
SINISCALCHI, S.M., CLEMENTS, M.A., GENTILE, A., VASSALLO, G., SORBELLO, F. (2006). A Study of Perceptron Mapping Capability to Design Speech Event Detectors. In Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on. (pp.805-808). IEEE.
Proceedings (atti dei congressi)
SINISCALCHI, SM; CLEMENTS, MA; GENTILE, A; VASSALLO, G; SORBELLO, F
File in questo prodotto:
File Dimensione Formato  
A STUDY OF PERCEPTRON MAPPING CAPABILITY.pdf

Solo gestori archvio

Dimensione 172.7 kB
Formato Adobe PDF
172.7 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10447/34281
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact