Publication

Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR

Publications associées (47)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Assessing the effectiveness of slides as a mean to improve the automatic transcription of oral presentations

Hervé Bourlard, Artem Peregoudov, Alessandro Vinciarelli

This paper presents experiments aiming at improving the automatic transcription of oral presentations through the inclusion of the slides in the recognition process. The experiments are performed over a data set of around three hours of material (~33 kword ...

IDIAP2006

Analysis of Error Recovery Schemes for Networks on Chips

Giovanni De Micheli, Luca Benini, Srinivasan Murali

In this article, we discuss design constraints to characterize efficient error recovery mechanisms for the NoC design environment. We explore error control mechanisms at the data link and network layers and present the schemes' architectural details. We in ...

Institute of Electrical and Electronics Engineers2005

Locally Testable Codes

Mahdi Cheraghchi Bashi Astaneh

Error correcting codes are combinatorial objects that allow reliable recovery of information in presence of errors by cleverly augmenting the original information with a certain amount of redundancy. The availability of efficient means of error detection i ...

2005

Noisy Text Categorization

Alessandro Vinciarelli

This work presents categorization experiments performed over noisy texts. By noisy it is meant any text obtained through an extraction process (affected by errors) from media other than digital texts (e.g. transcriptions of speech recordings extracted with ...

2005

Application of Information Retrieval Techniques to Single Writer Documents

Alessandro Vinciarelli

This work shows Information Retrieval experiments performed over handwritten documents produced by a single writer. The same retrieval task has been performed over both manual (no errors) and automatic (Word Error Rate around 45%) transcriptions of 200 han ...

2005

Effect of Recognition Errors on Information Retrieval Performance

Alessandro Vinciarelli

This work shows experiments on the retrieval of handwritten documents. The performance of the same state-of-the-art Information Retrieval system is compared when dealing with manual (no errors) and automatic (Word Error Rate around 50%) transcriptions of t ...

IDIAP2004

Effect of Recognition Errors on Information Retrieval Performance

Alessandro Vinciarelli

2004

On the Use of Information Retrieval Measures for Speech Recognition Evaluation

Hervé Bourlard, Daniel Gatica-Perez, John David Scott Dines, Darren Moore

This paper discusses the evaluation of automatic speech recognition (ASR) systems developed for practical applications, suggesting a set of criteria for application-oriented performance measures. The commonly used word error rate (WER), which poses ASR eva ...

IDIAP2004

Noisy Text Categorization

Alessandro Vinciarelli

IDIAP2004

Application of Information Retrieval Techniques to Single Writer Documents

Alessandro Vinciarelli

IDIAP2004