An extended experimental investigation of DNN uncertainty propagation for noise robust ASR

Karan Nathwani 1 Juan Morales-Cordovilla 2 Sunit Sivasankaran 1 Irina Illina 1 Emmanuel Vincent 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 UGR - Universidad de Granada
Abstract : Automatic speech recognition (ASR) in noisy environments remains a challenging goal. Recently, the idea of estimating the uncertainty about the features obtained after speech enhancement and propagating it to dynamically adapt deep neural network (DNN) based acoustic models has raised some interest. However, the results in the literature were reported on simulated noisy datasets for a limited variety of uncertainty estimators. We found that they vary significantly in different conditions. Hence, the main contribution of this work is to assess DNN uncertainty decoding performance for different data conditions and different uncertainty estimation/propagation techniques. In addition, we propose a neural network based uncertainty estima-tor and compare it with other uncertainty estimators. We report detailed ASR results on the CHiME-2 and CHiME-3 datasets. We find that, on average, uncertainty propagation provides similar relative improvement on real and simulated data and that the proposed uncertainty estimator performs significantly better than the one in [1]. We also find that the improvement is consistent, but it depends on the signal-to-noise ratio (SNR) and the noise environment.
Keywords : Robust ASR acoustic modeling DNN uncertainty estimation uncertainty propagation
Document type :
Conference papers
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download
https://hal.inria.fr/hal-01446441
Contributor : Emmanuel Vincent <>
Submitted on : Wednesday, January 25, 2017 - 11:59:18 PM
Last modification on : Wednesday, April 3, 2019 - 1:22:57 AM
Long-term archiving on: Wednesday, April 26, 2017 - 6:53:17 PM

File

nathwani_HSCMA17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01446441, version 1

Collections

CNRS | INRIA | LORIA-NLPKD | LORIA | UNIV-LORRAINE | GRID5000

Citation

Karan Nathwani, Juan Morales-Cordovilla, Sunit Sivasankaran, Irina Illina, Emmanuel Vincent. An extended experimental investigation of DNN uncertainty propagation for noise robust ASR. 5th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2017), Mar 2017, San Francisco, United States. ⟨hal-01446441⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

603

Files downloads

413

 

 

Contact

archive-ouverte@inria.fr