mlsanityData to 14 Oct 2026

Experiments on Turkish ASR with Self-Supervised Speech Representation Learning

arXiv 2210.07323 ↗First posted 13 Oct 2022cs.CL cs.LG cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

While the Turkish language is listed among low-resource languages, literature on Turkish automatic speech recognition (ASR) is relatively old. In this report, we present our findings on Turkish ASR with speech representation learning using HUBERT. We investigate pre-training HUBERT for Turkish with large-scale data curated from online resources. We pre-train our model using 6,500 hours of speech data from YouTube. The results show that the models are not ready for commercial use since they are not robust against disturbances that typically occur in real-world settings such as variations in accents, slang, background noise and interference. We analyze typical errors and the limitations of the models for use in commercial settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

13 of 23 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Layer Normalizationcited by 5,669
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  7. 2018Deep contextualized word representationscited by 2,290
  8. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  9. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 501
  10. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 467
  11. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  12. 2019Effectiveness of self-supervised pre-training for speech recognitioncited by 72
1 more
  1. 2020Learning Robust and Multilingual Speech Representationscited by 39

Built on by

Not cited yet.