analiza aiqbench
This study demonstrates that fine-tuning pretrained self-supervised models like Wav2Vec2 and HuBERT allows them to generalize effectively to rare phonemes, such as click consonants in Khoisan languages, which are often underrepresented in standard datasets. The findings suggest that self-supervised learning frameworks can overcome data scarcity biases to recognize typologically uncommon speech sounds with high accuracy.
Pretrained self-supervised speech models can recognize unseen consonants
arXiv:2606.11542v2 Announce Type: replace-cross 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.
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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2606.11542 [cs.CL]
(or arXiv:2606.11542v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.11542 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 222 cuvinte
Subiecte conexe
Pretrained self-supervised speech models can recognize unseen consonants
arXiv · 11 iun. 2026
From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing
arXiv · 15 iun. 2026
CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection
arXiv · 16 sept. 2026
ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
arXiv · 10 iun. 2026