Skip to Main content Skip to Navigation
Conference papers

When mismatched training data outperform matched data

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
Abstract : My talk will focus on robustness to background noise in distant-microphone speech recordings. I will introduce deep learning based techniques for speech enhancement and for acoustic modeling of speech. I will then report the results of a study on the impact of environment and microphone mismatches on the recognition accuracy. This study reveals that mismatched training data can sometimes outperform matched data. I will suggest a way to optimize the training set in order to exploit this finding.
Document type :
Conference papers
Complete list of metadata

Cited literature [4 references]  Display  Hide  Download
Contributor : Emmanuel Vincent Connect in order to contact the contributor
Submitted on : Sunday, September 17, 2017 - 8:56:33 PM
Last modification on : Wednesday, November 3, 2021 - 7:56:52 AM
Long-term archiving on: : Monday, December 18, 2017 - 1:06:08 PM


Files produced by the author(s)


  • HAL Id : hal-01588876, version 1


Emmanuel Vincent. When mismatched training data outperform matched data. Systematic approaches to deep learning methods for audio, Sep 2017, Vienna, Austria. ⟨hal-01588876⟩



Les métriques sont temporairement indisponibles