Detail publikace

Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems

BENEŠ, K. KOCOUR, M. BURGET, L.

Originální název

Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

End-to-end (e2e) systems have recently gained wide popularity in automatic speech recognition. However, these systems do generally not provide well-calibrated word-level confidences. In this paper, we propose Hystoc, a simple method for obtaining word-level confidences from hypothesis-level scores. Hystoc is an iterative alignment procedure which turns hypotheses from an n-best output of the ASR system into a confusion network. Eventually, word-level confidences are obtained as posterior probabilities in the individual bins of the confusion network. We show that Hystoc provides confidences that correlate well with the accuracy of the ASR hypothesis. Furthermore, we show that utilizing Hystoc in fusion of multiple e2e ASR systems increases the gains from the fusion by up to 1% WER absolute on Spanish RTVE2020 dataset. Finally, we experiment with using Hystoc for direct fusion of n-best outputs from multiple systems, but we only achieve minor gains when fusing very similar systems.

Klíčová slova

confidences measures, system fusion, end-toend systems, automatic speech recognition

Autoři

BENEŠ, K.; KOCOUR, M.; BURGET, L.

Vydáno

14. 4. 2024

Nakladatel

IEEE Signal Processing Society

Místo

Seoul

ISBN

979-8-3503-4485-1

Kniha

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Strany od

11276

Strany do

11280

Strany počet

5

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446739

BibTex

@inproceedings{BUT189696,
  author="Karel {Beneš} and Martin {Kocour} and Lukáš {Burget}",
  title="Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2024",
  pages="11276--11280",
  publisher="IEEE Signal Processing Society",
  address="Seoul",
  doi="10.1109/ICASSP48485.2024.10446739",
  isbn="979-8-3503-4485-1",
  url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446739"
}