Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Incorporating Error Level Noise Embedding for Improving LLM-Assisted Robustness in Persian Speech Recognition
Zahra Rahmani, Hossein Sameti
Automatic Speech Recognition (ASR) systems suffer significant performance degradation in noisy environments, a challenge that is especially severe for low-resource languages such a…
cs.CL2025
Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data
Sina Rashidi, Hossein Sameti
Direct speech-to-speech translation (S2ST), in which all components are trained jointly, is an attractive alternative to cascaded systems because it offers a simpler pipeline and l…
cs.CL2025
Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking
Mohammad Hossein Sameti, Sepehr Harfi Moridani, Ali Zarean +1
Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elev…