Detail publikačního výsledku

Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning

MOŠNER, L.; WU, M.; RAJU, A.; PARTHASARATHI, S.; KUMATANI, K.; SUNDARAM, S.; MAAS, R.; HOFFMEISTER, B.

Originální název

Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning

Anglický název

Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

For real-world speech recognition applications, noise robustnessis still a challenge. In this work, we adopt the teacherstudent(T/S) learning technique using a parallel clean andnoisy corpus for improving automatic speech recognition(ASR) performance under multimedia noise. On top of that,we apply a logits selection method which only preserves the khighest values to prevent wrong emphasis of knowledge fromthe teacher and to reduce bandwidth needed for transferringdata. We incorporate up to 8000 hours of untranscribed datafor training and present our results on sequence trained modelsapart from cross entropy trained ones. The best sequencetrained student model yields relative word error rate (WER)reductions of approximately 10.1%, 28.7% and 19.6% on ourclean, simulated noisy and real test sets respectively comparingto a sequence trained teacher.

Anglický abstrakt

For real-world speech recognition applications, noise robustnessis still a challenge. In this work, we adopt the teacherstudent(T/S) learning technique using a parallel clean andnoisy corpus for improving automatic speech recognition(ASR) performance under multimedia noise. On top of that,we apply a logits selection method which only preserves the khighest values to prevent wrong emphasis of knowledge fromthe teacher and to reduce bandwidth needed for transferringdata. We incorporate up to 8000 hours of untranscribed datafor training and present our results on sequence trained modelsapart from cross entropy trained ones. The best sequencetrained student model yields relative word error rate (WER)reductions of approximately 10.1%, 28.7% and 19.6% on ourclean, simulated noisy and real test sets respectively comparingto a sequence trained teacher.

Klíčová slova

automatic speech recognition, noise robustness,teacher-student training, domain adaptation

Klíčová slova v angličtině

automatic speech recognition, noise robustness,teacher-student training, domain adaptation

Autoři

MOŠNER, L.; WU, M.; RAJU, A.; PARTHASARATHI, S.; KUMATANI, K.; SUNDARAM, S.; MAAS, R.; HOFFMEISTER, B.

Rok RIV

2020

Vydáno

12.05.2019

Nakladatel

IEEE Signal Processing Society

Místo

Brighton

ISBN

978-1-5386-4658-8

Kniha

Proceedings of ICASSP

Strany od

6475

Strany do

6479

Strany počet

5

URL

https://ieeexplore.ieee.org/document/8683422

BibTex

@inproceedings{BUT160006,
  author="MOŠNER, L. and WU, M. and RAJU, A. and PARTHASARATHI, S. and KUMATANI, K. and SUNDARAM, S. and MAAS, R. and HOFFMEISTER, B.",
  title="Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning",
  booktitle="Proceedings of ICASSP",
  year="2019",
  pages="6475--6479",
  publisher="IEEE Signal Processing Society",
  address="Brighton",
  doi="10.1109/ICASSP.2019.8683422",
  isbn="978-1-5386-4658-8",
  url="https://ieeexplore.ieee.org/document/8683422"
}

Dokumenty

mosner_icassp2019_0006475