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. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICASSP.2006.1661398 | 2006 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-13 |
Keywords | Field | DocType |
automatic speech recognition,activation function,hidden markov models,support vector machines,artificial neural network,detectors,multi layer perceptron,signal detection,support vector machine,artificial neural networks,knowledge engineering,knowledge base,front end,svm,feed forward,speech recognition | Pattern recognition,Sigmoidal activation function,Detection theory,Computer science,Support vector machine,Speech recognition,Artificial intelligence,Knowledge engineering,Hidden Markov model,Artificial neural network,Detector,Perceptron | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.35 |
References | Authors | |
4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sabato Marco Siniscalchi | 1 | 310 | 30.21 |
Mark A. Clements | 2 | 486 | 64.32 |
Antonio Gentile | 3 | 63 | 10.63 |
Giorgio Vassallo | 4 | 122 | 21.04 |
Filippo Sorbello | 5 | 218 | 29.48 |