ASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects

Abstract:Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited target-speaker data is typically available, making full model retraining impractical. We present a component-level analysis of LoRA adaptation in Whisper, investigating how adapter placement interacts with the model size, training efficiency and utterance-duration in single-speaker settings. Our experimental comparative study shows that while scaling reduces errors, it does not eliminate mismatch. Furthermore, the full attention LoRa provides the most reliable accuracy, and the best time--accuracy trade-off. Improvements vary across utterance length, with medium-length recordings benefiting the most, while short and long utterances remain challenging. These findings highlight the importance of adaptation placement and duration-dependent evaluation, under challenging, data-scarce personalization scenarios.

Sound (cs.SD); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)

arXiv:2610.24572 [cs.SD]

(or arXiv:2610.24572v1 [cs.SD] for this version)

https://doi.org/10.48550/arXiv.2610.24572 Focus to learn more arXiv-issued DOI via DataCite

Speech and Computer, SPECOM 2026, Lecture Notes in Computer Science, vol. 16934, pp. 206-219, Springer, Cham (2027)

https://doi.org/10.1007/978-3-032-37867-5_15 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.