mlsanityData to 7 Oct 2026

Low-resource speech recognition and dialect identification of Irish in a multi-task framework

arXiv 2405.01293 ↗First posted 2 May 2024cs.CL cs.AI cs.SDcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper explores the use of Hybrid CTC/Attention encoder-decoder models trained with Intermediate CTC (InterCTC) for Irish (Gaelic) low-resource speech recognition (ASR) and dialect identification (DID). Results are compared to the current best performing models trained for ASR (TDNN-HMM) and DID (ECAPA-TDNN). An optimal InterCTC setting is initially established using a Conformer encoder. This setting is then used to train a model with an E-branchformer encoder and the performance of both architectures are compared. A multi-task fine-tuning approach is adopted for language model (LM) shallow fusion. The experiments yielded an improvement in DID accuracy of 10.8% relative to a baseline ECAPA-TDNN, and WER performance approaching the TDNN-HMM model. This multi-task approach emerges as a promising strategy for Irish low-resource ASR and DID.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

18 of 35 references.

References · 18

  1. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  2. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  3. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  4. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  5. 2020VoxLingua107: a Dataset for Spoken Language Recognitioncited by 118
  6. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  7. 2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 90
  8. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  9. 2020CTC-Segmentation of Large Corpora for German End-to-end Speech Recognitioncited by 75
  10. 2017Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Modelcited by 37
  11. 2023Improving Massively Multilingual ASR With Auxiliary CTC Objectivescited by 31
  12. 2021JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verificationcited by 21
6 more
  1. 2021OLR 2021 Challenge: Datasets, Rules and Baselinescited by 5
  2. 2023Towards dialect-inclusive recognition in a low-resource language: are balanced corpora the answer?cited by 5
  3. 2021AISPEECH-SJTU accent identification system for the Accented English Speech Recognition Challengecited by 4
  4. 2023A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learningcited by 4
  5. 2023Towards spoken dialect identification of Irishcited by 3
  6. 2017Phonetic Temporal Neural Model for Language Identificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Fotheidil: an Automatic Transcription System for the Irish Languagecited by 1
  2. 2024Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injectioncited by 0
  3. 2026Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusioncited by 0