4 papers
PersianVox: A Prosody-Aware Approach for Speech Dataset Generation from In-the-Wild Data
Saeedreza Zouashkiani, Soheil Khalesi, Saman Soleimani Roudi +2
Advancement of zero-shot text-to-speech synthesis is currently hindered for low-resource languages by the scarcity of large-scale, high-fidelity speech datasets. Traditional alignm…
A Versatile Framework for Designing Group-Sparse Adversarial Attacks
Alireza Heshmati, Saman Soleimani Roudi, Sajjad Amini +2
Existing adversarial attacks often neglect perturbation sparsity, limiting their ability to model structural changes and to explain how deep neural networks (DNNs) process meaningf…
Non-Intrusive Automatic Speech Recognition Refinement: A Survey
Mohammad Reza Peyghan, Saman Soleimani Roudi, Saeedreza Zouashkiani +3
Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibilit…
GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems
Amin Robatian, Mohammad Hajipour, Mohammad Reza Peyghan +4
Automatic Speech Recognition (ASR) systems have demonstrated remarkable performance across various applications. However, limited data and the unique language features of specific…