mlsanityData to 7 Oct 2026

Supervised Acoustic Embeddings And Their Transferability Across Languages

arXiv 2301.01020 ↗First posted 3 Jan 2023cs.CL cs.SD eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training has been proposed as a way to improve both supervised and unsupervised speech recognition, including frame-level feature representations and Acoustic Word Embeddings (AWE) for variable-length segments. However, self-supervised models alone cannot learn perfect separation of the linguistic content as they are trained to optimize indirect objectives. In this work, we experiment with different pre-trained self-supervised features as input to AWE models and show that they work best within a supervised framework. Models trained on English can be transferred to other languages with no adaptation and outperform self-supervised models trained solely on the target languages.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 3 Jan 2023.

Builds on

18 of 32 references.

References · 18

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  5. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  6. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 467
  7. 2021Unsupervised Speech Recognitioncited by 147
  8. 2020Unsupervised pretraining transfers well across languagescited by 100
  9. 2018Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speechcited by 52
  10. 2020Learning Robust and Multilingual Speech Representationscited by 39
  11. 2016Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencodercited by 34
  12. 2016The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognitioncited by 21
6 more
  1. 2021Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptationcited by 19
  2. 2020Neural Representations for Modeling Variation in Speechcited by 14
  3. 2020A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddingscited by 12
  4. 2020A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddingscited by 10
  5. 2020Multilingual acoustic word embedding models for processing zero-resource languagescited by 9
  6. 2021Unsupervised Automatic Speech Recognition: A Reviewcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023ArTST: Arabic Text and Speech Transformercited by 14