Publication

Combination of Acoustic Classifiers based on Dempster-Shafer Theory of evidence

Related publications (32)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networks

Ronan Collobert, Dimitri Palaz

In hybrid hidden Markov model/artificial neural networks (HMM/ANN) automatic speech recognition (ASR) system, the phoneme class conditional probabilities are estimated by first extracting acoustic features from the speech signal based on prior knowledge su ...

Idiap2013

A Neural Network based Regression Approach for Recognizing Simultaneous Speech

Hervé Bourlard, John David Scott Dines, Weifeng Li

This paper presents our approach for automatic speech recognition (ASR) of overlapping speech. Our system consists of two principal components: a speech separation component and a feature estmation component. In the speech separation phase, we first estima ...

IDIAP2008

Perception Studies on the Attributes of Synthetic Clear Speech for the Hard of Hearing

Chandra Sekhar Seelamantula

We make a case for ‘synthetic clear speech’ in the context of the persons with hearing impairment. We study the acoustic attributes of ‘clear speech’ that enable us to understand their importance in speech perception. Our perception experiments are motivat ...

IEEE2007

Analysis of Confusion Matrix to Combine Evidence for Phoneme Recognition

Hynek Hermansky, Joel Praveen Pinto

In this work we analyze and combine evidences from different classifiers for phoneme recognition using information from the confusion matrices. Speech signals are processed to extract the Perceptual Linear Prediction (PLP) and Multi-RASTA (MRASTA) features ...

IDIAP2007

Combination of Acoustic Classifiers based on Dempster-Shafer Theory of evidence

Hynek Hermansky, Fabio Valente

In this paper we investigate combination of neural net based classifiers using Dempster-Shafer Theory of Evidence. Under some assumptions, combination rule resembles a product of errors rule observed in human speech perception. Different combination are te ...

IDIAP2006

Robust audio segmentation

Jitendra Ajmera

Audio segmentation, in general, is the task of segmenting a continuous audio stream in terms of acoustically homogenous regions, where the rule of homogeneity depends on the task. This thesis aims at developing and investigating efficient, robust and unsup ...

EPFL2005

Robust Audio Segmentation

Hervé Bourlard, Jitendra Ajmera

IDIAP2004

Robust Audio Segmentation

Hervé Bourlard, Jitendra Ajmera

École Polytechnique Fédérale de Lausanne2004

Multi-stream adaptive evidence combination for noise robust ASR

Hervé Bourlard, Astrid Hagen

In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in psychoa ...

NORTH-HOLLAND2001

Error Correcting Posterior Combination for Robust Multi-Band Speech Recognition

Hervé Bourlard, Astrid Hagen

In human perception, the availability of context enhances recognition and renders it more robust to noise. Even if not all phonemes in a word (or words in a sentence etc.) are correctly perceived, humans can fill in missing parts with the help of cues from ...

2001