74 citations · 111 across the 33 of their papers we have counts for
39 papers
SyRA-CS: Synthetic-to-Real Adaptation for Code-Switched ASR with Meta-Learning
Fadel Thior, Ahmer Tabassum, Haania Siddiqui +2
Code-switched (CS) automatic speech recognition (ASR) remains difficult because real CS speech is scarce and synthetic speech does not fully match it. We investigate whether synthe…
Constrained CTC Decoding for Efficient Diacritic Restoration
Rufael Marew, Amr Keleg, Hanan Aldarmaki
In this work, we address diacritic restoration for Arabic speech transcripts. Most speech data are undiacritized, limiting the ability of modeling fine-grained phonological distinc…
What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR
Hawau Olamide Toyin, Srinivasan Umesh, Hanan Aldarmaki
ASR systems have been often reported to underperform on atypical speech. An often conflated compounding factor is the existence of two valid transcription references: verbatim (act…
Linear Semantic Segmentation for Low-Resource Spoken Dialects
Kirill Chirkunov, Younes Samih, Abed Alhakim Freihat +1
Semantic segmentation is a core component of discourse analysis, yet existing models are primarily developed and evaluated on high-resource written text, limiting their effectivene…
Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research
Taryn Wong, Zeerak Talat, Hanan Aldarmaki +1
Critical analyses of emotion recognition technology have raised ethical concerns around task validity and potential downstream impacts, urging researchers to ensure alignment betwe…
Aligning Stuttered-Speech Research with End-User Needs: Scoping Review, Survey, and Guidelines
Hawau Olamide Toyin, Mutiah Apampa, Toluwani Aremu +6
Atypical speech is receiving greater attention in speech technology research, but much of this work unfolds with limited interdisciplinary dialogue. For stuttered speech in particu…
Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs
Yara Alakeel, Chatrine Qwaider, Hanan Aldarmaki +1
This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing whether they captu…
Personal Attribute Leakage in Federated Speech Models
Hamdan Al-Ali, Ali Reza Ghavamipour, Tommaso Caselli +3
Federated learning is a common method for privacy-preserving training of machine learning models. In this paper, we analyze the vulnerability of ASR models to attribute inference a…
NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task
Bashar Talafha, Hawau Olamide Toyin, Peter Sullivan +9
We present the findings of the sixth Nuanced Arabic Dialect Identification (NADI 2025) Shared Task, which focused on Arabic speech dialect processing across three subtasks: spoken…
Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review
Maha Tufail Agro, Atharva Kulkarni, Karima Kadaoui +2
Motivated by a growing research interest into automatic speech recognition (ASR), and the growing body of work for languages in which code-switching (CS) often occurs, we present a…
Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Study
Hawau Olamide Toyin, Samar Mohamed Magdy, Hanan Aldarmaki
We investigate the effectiveness of large language models (LLMs) for text diacritization in two typologically distinct languages: Arabic and Yoruba. To enable a rigorous evaluation…
Clinical Annotations for Automatic Stuttering Severity Assessment
Ana Rita Valente, Rufael Marew, Hawau Olamide Toyin +6
Stuttering is a complex disorder that requires specialized expertise for effective assessment and treatment. This paper presents an effort to enhance the FluencyBank dataset with a…
ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis
Hawau Olamide Toyin, Rufael Marew, Humaid Alblooshi +2
We introduce ArVoice, a multi-speaker Modern Standard Arabic (MSA) speech corpus with diacritized transcriptions, intended for multi-speaker speech synthesis, and can be useful for…
Voice of a Continent: Mapping Africa's Speech Technology Frontier
AbdelRahim Elmadany, Sang Yun Kwon, Hawau Olamide Toyin +3
Africa's rich linguistic diversity remains significantly underrepresented in speech technologies, creating barriers to digital inclusion. To alleviate this challenge, we systematic…
SPIRIT: Patching Speech Language Models against Jailbreak Attacks
Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui +2
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech sign…
JEEM: Vision-Language Understanding in Four Arabic Dialects
Karima Kadaoui, Hanin Atwany, Hamdan Al-Ali +7
We introduce JEEM, a benchmark designed to evaluate Vision-Language Models (VLMs) on visual understanding across four Arabic-speaking countries: Jordan, The Emirates, Egypt, and Mo…
Infant Cry Detection Using Causal Temporal Representation
Minghao Fu, Danning Li, Aryan Gadhiya +8
This paper addresses a major challenge in acoustic event detection, in particular infant cry detection in the presence of other sounds and background noises: the lack of precise an…
SparQLe: Speech Queries to Text Translation Through LLMs
Amirbek Djanibekov, Hanan Aldarmaki
With the growing influence of Large Language Models (LLMs), there is increasing interest in integrating speech representations with them to enable more seamless multi-modal process…
Dialectal Coverage And Generalization in Arabic Speech Recognition
Amirbek Djanibekov, Hawau Olamide Toyin, Raghad Alshalan +2
Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard…
STTATTS: Unified Speech-To-Text And Text-To-Speech Model
Hawau Olamide Toyin, Hao Li, Hanan Aldarmaki
Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two…
RelUNet: Relative Channel Fusion U-Net for Multichannel Speech Enhancement
Ibrahim Aldarmaki, Thamar Solorio, Bhiksha Raj +1
Neural multi-channel speech enhancement models, in particular those based on the U-Net architecture, demonstrate promising performance and generalization potential. These models ty…
PALM: Few-Shot Prompt Learning for Audio Language Models
Asif Hanif, Maha Tufail Agro, Mohammad Areeb Qazi +1
Audio-Language Models (ALMs) have recently achieved remarkable success in zero-shot audio recognition tasks, which match features of audio waveforms with class-specific text prompt…
Mixat: A Data Set of Bilingual Emirati-English Speech
Maryam Al Ali, Hanan Aldarmaki
This paper introduces Mixat: a dataset of Emirati speech code-mixed with English. Mixat was developed to address the shortcomings of current speech recognition resources when appli…
Automatic Restoration of Diacritics for Speech Data Sets
Sara Shatnawi, Sawsan Alqahtani, Hanan Aldarmaki
Automatic text-based diacritic restoration models generally have high diacritic error rates when applied to speech transcripts as a result of domain and style shifts in spoken lang…