Publication detail

Towards Automatic Methods to Detect Errors in Transcriptions of Speech Recordings

YANG, J. ONDEL YANG, L. MANOHAR, V. HEŘMANSKÝ, H.

Original Title

Towards Automatic Methods to Detect Errors in Transcriptions of Speech Recordings

Type

conference paper

Language

English

Original Abstract

This work explores different methods to detect errors in transcriptions of speech recordings. We artificially corrupt well transcribed speech transcriptions with three types of errors: substitution, insertion and deletion on TIMIT phonemic transcriptions and WSJ word transcriptions. First, we use Bayesian model selection method by comparing the log-likelihoods from alignment and phone recognizer, a final score is computed to make decision. In this method, we consider two models, Bayesian Hidden Markov Model (HMM) and a Variational Auto-Encoder (VAE) combined with a HMM. Alternately, we build a biased ASR system with language models trained on individual transcriptions, detection decision is based on Levenshtein distance (LD) between transcription and oracle path from decoded lattice. We evaluate the methods of detecting errors in corrupted TIMIT transcription, the best result (either using model selection with VAE model or biased ASR) achieves 7% equal error rate on the Detection Error Tradeoff (DET) curve; we also evaluate the methods of detecting errors in corrupted WSJ transcriptions, and the best result (using biased ASR) achieves 3% equal error rate.

Keywords

Transcription error detection, model selection, HMM-GMM, Variational Auto-Encoder, detection error tradeoff

Authors

YANG, J.; ONDEL YANG, L.; MANOHAR, V.; HEŘMANSKÝ, H.

Released

12. 5. 2019

Publisher

IEEE Signal Processing Society

Location

Brighton

ISBN

978-1-5386-4658-8

Book

Proceedings of ICASSP

Pages from

3747

Pages to

3751

Pages count

5

URL

BibTex

@inproceedings{BUT160007,
  author="YANG, J. and ONDEL YANG, L. and MANOHAR, V. and HEŘMANSKÝ, H.",
  title="Towards Automatic Methods to Detect Errors in Transcriptions of Speech Recordings",
  booktitle="Proceedings of ICASSP",
  year="2019",
  pages="3747--3751",
  publisher="IEEE Signal Processing Society",
  address="Brighton",
  doi="10.1109/ICASSP.2019.8683722",
  isbn="978-1-5386-4658-8",
  url="https://ieeexplore.ieee.org/document/8683722"
}