Exploration de réseaux de neurones à décharges dans un contexte de reconnaissance de parole /

Loiselle, Stéphane

doi:10.1522/18186435

Search citation statements

Order By: Relevance

Paper Sections

Select...

Speech Recognition With Ensemble Interval Histograms1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2005

2022

Publication Types

Select...

Other1

Book1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The peripheral auditory system is crudely modelised and it is assumed that the auditory image representation can be processed as images. From preliminary experiments [99], it is observed that bio-inspired approaches could be a good complement to statistical speech recognisers as they might reach very quickly acceptable results on very limited training sets.…”

Section: Speech Recognition With Ensemble Interval Histogramsmentioning

confidence: 99%

Perceptive, non-linear Speech Processing and Spiking Neural Networks

Rouat,

Pichevar,

Loiselle

2022

Preprint

View full text Add to dashboard Cite

Source separation and speech recognition are very difficult in the context of noisy and corrupted speech. Most conventional techniques need huge databases to estimate speech (or noise) density probabilities to perform separation or recognition. We discuss the potential of perceptive speech analysis and processing in combination with biologically plausible neural network processors. We illustrate the potential of such non-linear processing of speech on a source separation system inspired by an Auditory Scene Analysis paradigm. We also discuss a potential application in speech recognition.

show abstract

Section: Speech Recognition With Ensemble Interval Histogramsmentioning

confidence: 99%