Skip to Main content Skip to Navigation
Conference papers

Robust ASR using neural network based speech enhancement and feature simulation

Sunit Sivasankaran 1 Aditya Nugraha 1 Emmanuel Vincent 1 Juan Andrés Morales Cordovilla 1 Siddharth Dalmia 1 Irina Illina 1 Antoine Liutkus 2
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We consider the problem of robust automatic speech recognition (ASR) in the context of the CHiME-3 Challenge. The proposed system combines three contributions. First, we propose a deep neural network (DNN) based multichannel speech enhancement technique, where the speech and noise spectra are estimated using a DNN based regressor and the spatial parameters are derived in an expectation-maximization (EM) like fashion. Second, a conditional restricted Boltz-mann machine (CRBM) model is trained using the obtained enhanced speech and used to generate simulated training and development datasets. The goal is to increase the similarity between simulated and real data, so as to increase the benefit of multicondition training. Finally, we make some changes to the ASR backend. Our system ranked 4th among 25 entries
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download

https://hal.inria.fr/hal-01204553
Contributor : Sunit Sivasankaran <>
Submitted on : Thursday, September 24, 2015 - 11:54:07 AM
Last modification on : Monday, May 4, 2020 - 11:37:33 AM
Long-term archiving on: : Tuesday, December 29, 2015 - 9:43:47 AM

File

INRIA.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01204553, version 1

Citation

Sunit Sivasankaran, Aditya Nugraha, Emmanuel Vincent, Juan Andrés Morales Cordovilla, Siddharth Dalmia, et al.. Robust ASR using neural network based speech enhancement and feature simulation. ASRU, Dec 2015, Arizona, United States. ⟨hal-01204553⟩

Share

Metrics

Record views

911

Files downloads

1759