1 code implementation • 5 Feb 2025 • Yassine El Kheir, Youness Samih, Suraj Maharjan, Tim Polzehl, Sebastian Möller
This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and scene-based deepfake scenarios.
no code implementations • 20 Nov 2024 • Houssam Eddine-Othman Lachemat, Akli Abbas, Nourredine Oukas, Yassine El Kheir, Samia Haboussi, Absar Showdhury Shammur
The paper introduces and publicly releases (Data download link available after acceptance) CAFE -- the first Code-switching dataset between Algerian dialect, French, and english languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 5 Aug 2024 • Yassine El Kheir, Hamdy Mubarak, Ahmed Ali, Shammur Absar Chowdhury
Phonetically correct transcribed speech resources for dialectal Arabic are scarce.
no code implementations • 21 Oct 2023 • Yassine El Kheir, Ahmed Ali, Shammur Absar Chowdhury
Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years.
no code implementations • 14 Sep 2023 • Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
Research on pronunciation assessment systems focuses on utilizing phonetic and phonological aspects of non-native (L2) speech, often neglecting the rich layer of information hidden within the non-verbal cues.
no code implementations • 14 Sep 2023 • Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
The phonological discrepancies between a speaker's native (L1) and the non-native language (L2) serves as a major factor for mispronunciation.
no code implementations • 23 Jul 2023 • Yousseif Elshahawy, Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali
Furthermore, the platform offers flexibility to admin roles to add new data or tasks beyond dialectal speech and word collection, which are displayed to contributors.
no code implementations • 24 May 2023 • Ahmed Abdelali, Hamdy Mubarak, Shammur Absar Chowdhury, Maram Hasanain, Basel Mousi, Sabri Boughorbel, Yassine El Kheir, Daniel Izham, Fahim Dalvi, Majd Hawasly, Nizi Nazar, Yousseif Elshahawy, Ahmed Ali, Nadir Durrani, Natasa Milic-Frayling, Firoj Alam
Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.
no code implementations • 9 May 2023 • Yassine El Kheir, Fouad Khnaisser, Shammur Absar Chowdhury, Hamdy Mubarak, Shazia Afzal, Ahmed Ali
This paper introduces a novel Arabic pronunciation learning application QVoice, powered with end-to-end mispronunciation detection and feedback generator module.
no code implementations • 2 Nov 2022 • Yassine El Kheir, Shammur Absar Chowdhury, Ahmed Ali, Hamdy Mubarak, Shazia Afzal
Our proposed technique achieves state-of-the-art results, with Speechocean762, on ASR dependent mispronunciation detection models at phoneme level, with a 2. 0% gain in Pearson Correlation Coefficient (PCC) compared to the previous state-of-the-art [1].
Ranked #4 on
Phone-level pronunciation scoring
on speechocean762