collaborators

5 papers

cs.CL2026

A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationales

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

Automated L2 speech assessment can assign proficiency labels, but often lacks interpretability. We propose a rubric-guided SpeechLLM for multi-aspect, multi-granular assessment, tr…

cs.CL2026

Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

Reliable and interpretable automated assessment of second-language (L2) speech remains a central challenge, as large speech-language models (SpeechLLMs) often struggle to align wit…

eess.AS2026

Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

An accurate assessment of L2 English pronunciation is crucial for language learning, as it provides personalized feedback and ensures a fair evaluation of individual progress. Howe…

eess.AS2025

Evaluating Logit-Based GOP Scores for Mispronunciation Detection

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

Pronunciation assessment relies on goodness of pronunciation (GOP) scores, traditionally derived from softmax-based posterior probabilities. However, posterior probabilities may su…

eess.AS2025

Enhancing GOP in CTC-Based Mispronunciation Detection with Phonological Knowledge

Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1

Computer-Assisted Pronunciation Training (CAPT) systems employ automatic measures of pronunciation quality, such as the goodness of pronunciation (GOP) metric. GOP relies on forced…