Enhancing Automatic Speech Recognition: Effects of Semantic Audio Filtering on Models Performance

Y Perezhohin, T Santos, V Costa, F Peres… - IEEE …, 2024 - ieeexplore.ieee.org
This paper presents a novel methodology for enhancing Automatic Speech Recognition
(ASR) performance by utilizing contrastive learning to filter synthetic audio data. We address …

Optimizing Whisper models for Amazigh ASR: a comparative analysis

M Daouad, F Ataa Allah, EW Dadi - International Journal of Speech …, 2024 - Springer
Abstract Recent breakthroughs in Natural Language Processing have significantly
enhanced the presence of Automatic Speech Recognition (ASR) systems in daily life. The …

Parameter-efficient fine-tuning of Whisper for low-resource speech recognition

Y Liu, D Qu - 2024 5th International Seminar on Artificial …, 2024 - ieeexplore.ieee.org
Limited data availability remains a significant challenge for Whisper's low-resource speech
recognition performance, falling short of practical application requirements. While previous …

Does Whisper understand Swiss German? An automatic, qualitative, and human evaluation

EL Dolev, CF Lutz, N Aepli - arXiv preprint arXiv:2404.19310, 2024 - arxiv.org
Whisper is a state-of-the-art automatic speech recognition (ASR) model (Radford et al.,
2022). Although Swiss German dialects are allegedly not part of Whisper's training data …

[PDF][PDF] Towards an ASR System for Documenting Endangered Languages: A Preliminary Study on Sardinian

I Chizzoni, A Vietti - 2024 - ceur-ws.org
Speech recognition systems are still highly dependent on textual orthographic resources,
posing a challenge for low-resource languages. Recent research leverages self-supervised …

[PDF][PDF] Projektarbeit (Informatik)

L Bolliger, S Waldburger, M Cieliebak - zhaw.ch
For multilingual systems that need to understand language, the differentiation of languages
and dialects is an important component. For low-resource languages such as Swiss …