Pretrained self-supervised speech models can recognize unseen consonants

• URL: http://arxiv.org/abs/2606.11542v1
• Date: Wed, 10 Jun 2026 01:07:32 GMT
• Title: Pretrained self-supervised speech models can recognize unseen consonants
• Abstract summary: We fine-tune and compare pretrained self-supervised speech models on data from two click-rich Khoisan languages.<n>Our results reveal that the fine-tuned models consistently recognize clicks more accurately than non-clicks.
• Score: 12.87864634250355
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward high-resource languages with little data from low-resource languages, raising concerns about the potential underrepresentation of typologically uncommon speech sounds such as click consonants primarily found in Khoisan languages. This leads to our central research question: Can these models recognize click consonants as accurately as other speech sounds? To address this question, we fine-tune and compare pretrained self-supervised speech models (Wav2Vec2 and HuBERT) on data from two click-rich Khoisan languages (G|ui and West !Xoon). Our results reveal that the fine-tuned models consistently recognize clicks more accurately than non-clicks, suggesting that self-supervision enables generalization across human speech sounds including rare phonemes.

Related papers

• Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models [5.874344393486844]
  We show how wav2vec2 models trained on four different languages encode both language-matched and non-matched speech.<n>Our findings suggest that the structure of representations learned by wav2vec2 is largely independent of the speech material used during pretraining.
  arXiv  Detail & Related papers  (2025-06-12T16:16:38Z)
• Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach [14.5696754689252]
  Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. We show that fine-tuning speech representation models on phoneme classification leads to more context-invariant representations.
  arXiv  Detail & Related papers  (2024-09-16T10:29:15Z)
• Natural language guidance of high-fidelity text-to-speech with synthetic annotations [13.642358232817342]
  We propose a scalable method for labeling various aspects of speaker identity, style, and recording conditions. We then apply this method to a 45k hour dataset, which we use to train a speech language model. Our results demonstrate high-fidelity speech generation in a diverse range of accents, prosodic styles, channel conditions, and acoustic conditions.
  arXiv  Detail & Related papers  (2024-02-02T21:29:34Z)
• Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching [65.74653592668743]
  Finetuning self-supervised multilingual representations reduces absolute word error rates by up to 20%. In circumstances with limited training data finetuning self-supervised representations is a better performing and viable solution.
  arXiv  Detail & Related papers  (2023-11-25T17:05:21Z)
• Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer [53.72998363956454]
  Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy. The scarcity of high-quality speaker-parallel data poses a challenge for learning style transfer during translation. We design an S2ST pipeline with style-transfer capability on the basis of discrete self-supervised speech representations and timbre units.
  arXiv  Detail & Related papers  (2023-09-14T09:52:08Z)
• AudioPaLM: A Large Language Model That Can Speak and Listen [79.44757696533709]
  We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models. It can process and generate text and speech with applications including speech recognition and speech-to-speech translation.
  arXiv  Detail & Related papers  (2023-06-22T14:37:54Z)
• Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models [14.887781621924255]
  This paper is the first attempt to extend the use of pre-trained models into word-level zero-resource speech recognition. It is done by fine-tuning the pre-trained models on IPA phoneme transcriptions and decoding with a language model trained on extra texts. Experiments on Wav2vec 2.0 and HuBERT models show that this method can achieve less than 20% word error rate on some languages.
  arXiv  Detail & Related papers  (2022-10-13T12:11:18Z)
• The Ability of Self-Supervised Speech Models for Audio Representations [53.19715501273934]
  Self-supervised learning (SSL) speech models have achieved unprecedented success in speech representation learning. We conduct extensive experiments on abundant speech and non-speech audio datasets to evaluate the representation ability of state-of-the-art SSL speech models. Results show that SSL speech models could extract meaningful features of a wide range of non-speech audio, while they may also fail on certain types of datasets.
  arXiv  Detail & Related papers  (2022-09-26T15:21:06Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)
• Towards Zero-shot Learning for Automatic Phonemic Transcription [82.9910512414173]
  A more challenging problem is to build phonemic transcribers for languages with zero training data. Our model is able to recognize unseen phonemes in the target language without any training data. It achieves 7.7% better phoneme error rate on average over a standard multilingual model.
  arXiv  Detail & Related papers  (2020-02-26T20:38:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.