AlTaei, Mohammed Hameed Ahmed, Hamad, Mohamed Fadlalla Elhaj, Al Hashimi, Omar ORCID: https://orcid.org/0000-0001-8565-2144 and Samawi, Ameer Hakim (2026) Self-supervised Wav2Vec representations integrated with transformers for speech-to-text applications. In: 7th International Conference on AI in Computational Linguistics, 6 – 7 Dec 2025, Dubai, UAE.

Preview

PDF Al HashimiO_Self-Supervised Wav2Vec Representations Integrated_VoR.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (636kB) | Preview

Abstract

Traditional ASR systems often struggle with low-resource languages, data dependence, and robustness in noisy or domain-specific environments. Telemedicine, clinical recordkeeping, and multilingual communication depend on accurate speech-to-text systems. This work introduces Wav2Vec-RCNet, a novel ASR architecture that integrates self-supervised Wav2Vec representations with recurrent neural networks (RNNs) and combines Cuckoo Search-tuned RNNs. Contrastive predictive coding lets Wav2Vec generate high-dimensional latent embeddings from raw audio. This is possible because effective feature representations do not require large annotated corpora. LSTM and GRU embeddings capture the temporal and sequential connections needed for accurate voice transcription. The Lévy flight-based search dynamics of Cuckoo Search optimise learning rates, hidden unit dimensions, dropout probabilities, and attention weight distributions for optimum performance. Wav2Vec-RCNet outperforms clinical benchmark datasets, multi-accent datasets, and conventional supervised and hybrid ASR systems in terms of word and character error rates. Wav2Vec-RCNet constructs a scalable, resource-efficient, and domain-adaptive framework for real-world speech-to-text applications, leveraging self-supervised feature learning, recurrent sequence modeling, and metaheuristic-driven optimization.

Item Type:	Conference or Workshop Item (Paper)
ISSN:	1877-0509
Page Range:	pp. 550-557
Identifier:	10.1016/j.procs.2026.01.064
Keywords:	Self-Supervised Learning, Wav2Vec Representations, Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Cuckoo Search Optimization, Speech-to-Text Applications, Automatic Speech Recognition (ASR)
Subjects:	Computing > Intelligent systems
Related URLs:	https://www.aclweb.org/portal/content/7t...
Date Deposited:	30 Oct 2026
Dates:	Date Publication status 26 March 2026 Published Online 7 December 2025 Presented
School, department or research centre:	School of Computing and Engineering
Keywords:	Self-Supervised Learning, Wav2Vec Representations, Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Cuckoo Search Optimization, Speech-to-Text Applications, Automatic Speech Recognition (ASR)
URI:	https://repository.uwl.ac.uk/id/eprint/15728

Downloads

Actions (admin access)