Publication
Transcribing Mandarin Broadcast Speech Using Multi-Layer Perceptron Acoustic Features
Publications associées (41)
MLP-based Log Spectral Energy Mapping for Robust Overlapping Speech Recognition
Hervé Bourlard, John David Scott Dines, Weifeng Li
This paper investigates a multilayer perceptron (MLP) based acoustic feature mapping to extract robust features for automatic speech recognition (ASR) of overlapping speech. The MLP is trained to learn the mapping from log mel filter bank energies (MFBEs) ...
IDIAP2007The segmentation of multi-channel meeting recordings for automatic speech recognition
One major research challenge in the domain of the analysis of meeting room data is the automatic transcription of what is spoken during meetings, a task which has gained considerable attention within the ASR research community through the NIST rich transcr ...
2006The segmentation of multi-channel meeting recordings for automatic speech recognition
One major research challenge in the domain of the analysis of meeting room data is the automatic transcription of what is spoken during meetings, a task which has gained considerable attention within the ASR research community through the NIST rich transcr ...
IDIAP2006Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR
In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Multilaye ...
IDIAP2000Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR
In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Multilaye ...
2000On the Complexity of Recognizing Regions Computable by Two-Layered Perceptrons
This work is concerned with the computational complexity of the recognition of , the class of regions of the Euclidian space that can be classified exactly by a two-layered perceptron. Some subclasses of of particular interest are also studi ...
1999On the Complexity of Recognizing Regions Computable by Two-Layered Perceptrons
This work is concerned with the computational complexity of the recognition of , the class of regions of the Euclidian space that can be classified exactly by a two-layered perceptron. Some subclasses of of particular interest are also studi ...
IDIAP1998Optimal Setting of Weights, Learning Rate, and Gain
The optimal setting of the initial weights, learning rate, and gain of the activation function, which are key parameters of a neural network, influencing training time and generalization performance, are investigated by means of a large number of experimen ...
IDIAP1997High Order and Multilayer Perceptron Initialization
Proper initialization is one of the most important prerequisites for fast convergence of feed-forward neural networks like high order and multilayer perceptrons. This publication aims at determining the optimal variance (or range) for the initial weights a ...
IEEE1997A Method for All-Positive Optical Multilayer Perceptrons
The most promising approaches for optical neural networks are based on intensity encoding. However, a serious drawback of intensity encoding is the lack of negative values and optical subtraction, which are essential for rendering neural networks useful. T ...
IEEE1996