Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Pretrained self-supervised speech models can recognize unseen consonants

Domain:

natural language processing

Record type:

papermodel
Creator:
TagFerNakOno
Host:avatar
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. 6 pages, 3 figures, 3 tables, accepted at Interspeech 2026

Visit

arxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

Tshuwau

Tags

Computation and LanguageArtificial Intelligence

Similar

Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic ModelsBenchmarking Self-Supervised Speech Models on Multilingual Nigerian SpeechDo self-supervised speech models develop human-like perception biases?Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech ModelsEmploying self-supervised learning models for cross-linguistic child speech maturity classificationComparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models

Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models

In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretr

Benchmarking Self-Supervised Speech Models on Multilingual Nigerian Speech

Self-supervised speech models such as Whisper and wav2vec 2.0 have significantly advanced automatic

Do self-supervised speech models develop human-like perception biases?

Self-supervised models for speech processing form representational spaces without using any external

Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models

Given the strong results of self-supervised models on various tasks, there have been surprisingly fe

Employing self-supervised learning models for cross-linguistic child speech maturity classification

International audience Speech technology systems struggle with many downstream tasks

Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models

International audience This paper investigates the potential of improving a hybrid au