| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition
Abstract : The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors. Usually, either a quality control stage discards transcriptions with too many errors, or the noisy transcriptions are used as is. We introduce Lead2Gold, a method to train an ASR system that exploits the full potential of noisy transcriptions. Based on a noise model of transcription errors, Lead2Gold searches for better transcriptions of the training data with a beam search that takes this noise model into account. The beam search is differentiable and does not require a forced alignment step, thus the whole system is trained end-to-end. Lead2Gold can be viewed as a new loss function that can be used on top of any sequence-to-sequence deep neural network. We conduct proof-of-concept experiments on noisy transcriptions generated from letter corruptions with different noise levels. We show that Lead2Gold obtains a better ASR accuracy than a competitive baseline which does not account for the (artificially-introduced) transcription noise.
Cited literature [30 references]
https://hal.inria.fr/hal-02316572
Contributor : Adrien Dufraux <>
Submitted on : Tuesday, October 15, 2019 - 2:03:06 PM
Last modification on : Friday, October 18, 2019 - 1:25:27 PM
Long-term archiving on: : Friday, January 17, 2020 - 8:40:10 AM
Contributor : Adrien Dufraux <>
Submitted on : Tuesday, October 15, 2019 - 2:03:06 PM
Last modification on : Friday, October 18, 2019 - 1:25:27 PM
Long-term archiving on: : Friday, January 17, 2020 - 8:40:10 AM
File
CAMERA_READY_ASRU_submission.p...
Files produced by the author(s)