Automatic speech processing
EE-554
End-to-End Acoustic Modeling using Convolutional Neural Networks for HMM-based Automatic Speech Recognition by Palaz, Magimai-Doss and Collobert
This page is part of the content downloaded from End-to-End Acoustic Modeling using Convolutional Neural Networks for HMM-based Automatic Speech Recognition by Palaz, Magimai-Doss and Collobert on Wednesday, 25 December 2024, 16:58. Note that some content and any files larger than 50 MB are not downloaded.
Description
In the lecture, we briefly discussed about the use of neural networks to learn feature representation. Here is a paper about learning feature representations automatically in a task dependent manner using neural networks. This paper was published in the Journal of Speech Communication in 2019.
https://www.sciencedirect.com/science/article/pii/S0167639316301625
This paper should be accessible from with in EPFL. I putting a pdf version in case you are not able to access it.
A video lecture "Raw Waveform-based Acoustic Modeling and its analysis" based on this and following works can be found at
https://portal.klewel.com/watch/webcast/tapas-training-event-2-day4/talk/1/