| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
When mismatched training data outperform matched data
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.
Cited literature [4 references]
https://hal.inria.fr/hal-01588876
Contributor : Emmanuel Vincent <>
Submitted on : Sunday, September 17, 2017 - 8:56:33 PM
Last modification on : Monday, May 4, 2020 - 11:37:45 AM
Document(s) archivé(s) le : Monday, December 18, 2017 - 1:06:08 PM
Contributor : Emmanuel Vincent <>
Submitted on : Sunday, September 17, 2017 - 8:56:33 PM
Last modification on : Monday, May 4, 2020 - 11:37:45 AM
Document(s) archivé(s) le : Monday, December 18, 2017 - 1:06:08 PM
File
vincent_ESI17.pdf
Files produced by the author(s)