mlsanityData to 7 Oct 2026

Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition

arXiv 2203.16823 ↗First posted 31 Mar 2022cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

In the recent years end to end (E2E) automatic speech recognition (ASR) systems have achieved promising results given sufficient resources. Even for languages where not a lot of labelled data is available, state of the art E2E ASR systems can be developed by pretraining on huge amounts of high resource languages and finetune on low resource languages. For a lot of low resource languages the current approaches are still challenging, since in many cases labelled data is not available in open domain. In this paper we present an approach to create labelled data for Maithili, Bhojpuri and Dogri by utilising pseudo labels from text to speech for forced alignment. The created data was inspected for quality and then further used to train a transformer based wav2vec 2.0 ASR model. All data and models are available in open domain.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 6 of its 13 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

6 of 13 references.

References · 6

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  3. 2017Generalized End-to-End Loss for Speaker Verificationcited by 290
  4. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  5. 2021CLSRIL-23: Cross Lingual Speech Representations for Indic Languagescited by 22
  6. 2017Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Modelcited by 6

Built on by

Not cited yet.