Can Large Audio-Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities [Archival]
Heejoon Koo
Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models [Archival]
Maneesha Rani Saha; Catherine Bao; Neal Patwari
Temporal Taxation Compounds Under Post-Training Compression of Whisper Models [Archival]
Srishti Ginjala; Eric Fosler-Lussier; Christopher W. Myers; Srinivasan Parthasarathy
What Drives Dialectal Jailbreaks? An Ablation of Surface Form, Cultural Framing, and Strategy Banks [Archival]
Qingyang Xu
Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs [Archival]
Ganesh Pavan Kartikeya Bharadwaj Kolluri; Michael Kampouridis; Ravi Shekhar
TurkSV-Bench: Assessing Demographic Bias and Preprocessing Effects in Speaker Verification [Archival]
Ahmet Berkay Kantarcı; Abdulkadir Parlak; Ahmet Karazor
Lost in Compression: Calibration Bias and the Accent-WER Gap in Speech LLMs [Archival]
Angad Ripudaman Singh Bajwa
A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models [Archival]
Nicolas Bourrel; Abderrahmane Issam; Gerasimos Spanakis
AIP-Speech: Auditing Speech LLM Robustness to Background Interference [Archival]
Aiden Dsouza; Shreyansh Mishra; Yashraj Suneja; Rohan Swain; Samyak Borkar; Arjun Jaishankar; Tanmay Urade
Early Warning for Target-Speaker Extraction: Reliability under Distribution and Failure-Definition Shift [Archival]
Shubham Sharma; Manik Gupta
Detecting Mental Manipulation in Speech via Synthetic Multi-Speaker Dialogue [Non-Archival]
Run Chen; Wen Liang; Ziwei Gong; Lin Ai; Julia Hirschberg
KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models [Non-Archival]
Tuan Dat Phuong
Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges [Non-Archival]
Syeda Faiza Ahmed Sara; Zien Sheikh Ali; Hunzalah Hassan Bhatti; Firoj Alam; Shammur Absar Chowdhury
Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear? [Non-Archival]
Kshitij Ambilduke; Caroline Brun; Thibaut Thonet; Vassilina Nikoulina; Marcely Zanon Boito
Evaluating WhisperX Transcriptions of Korean Child-Directed Speech through Linguistic Analysis [Non-Archival]
Ioana Buhnila; Jiho Lee; Sung Hyu Chon; Jae-Hun Jung; Eon-Suk Ko
Auditing Spoken Correction Uptake and Retention in Speech LLMs [Non-Archival]
Yoonhyuk Choi
Dialect Gaps in Tamil Speech Recognition: A Paired Evaluation of Erode and Common Spoken Tamil [Non-Archival]
Dharunish Yugeswardeenoo
Steering ASR systems towards domain adaptation and personalization [Non-Archival]
Felix Herron; Alex Colagrande; Solange Rossato; François Portet; Alexandre Allauzen; Chuyan Li
Responsible Benchmarking of Fairness for Automatic Speech Recognition [Non-Archival]
Felix Herron; Ange Richard; François Portet; Alexandre Allauzen; Solange Rossato
Zero-Shot Spoken Language Understanding with SLAM-ASR: What Do Monolingual ASR-Trained Linear Projectors Enable? [Non-Archival]
Edwin Arkel Rios; Sneh Sourabh; Jocelyn Zaruma; Girish Ewoorkar; Julian Mack; Bo-Cheng Lai