Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

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.
Fichier principal
Vignette du fichier
CAMERA_READY_ASRU_submission.pdf (217.76 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02316572 , version 1 (15-10-2019)

Identifiers

  • HAL Id : hal-02316572 , version 1

Cite

Adrien Dufraux, Emmanuel Vincent, Awni Hannun, Armelle Brun, Matthijs Douze. Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition. ASRU 2019 - IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2019, Singapour, Singapore. ⟨hal-02316572⟩
120 View
424 Download

Share

Gmail Facebook Twitter LinkedIn More