Whisper-based speaker-role and language diarization systems to automatically extract respondent speech and characterize language usage in multilingual interviews with older adults and whether diarization-derived conversational and language-use behaviors can support downstream language proficiency assessment are developed.
Abstract
Automatic language proficiency assessment in the context of multilingual interview-based settings remains underexplored. In this work, we develop Whisper-based speaker-role and language diarization systems to automatically extract respondent speech and characterize language usage in multilingual interviews with older adults. We further investigate whether diarization-derived conversational and language-use behaviors can support downstream language proficiency assessment. Results show that language-adapted Whisper models substantially improve language diarization performance for lower-resource and linguistically related Indian languages. Statistical analyses reveal that respondent speech ratio and intended language usage are strong predictors of proficiency ratings. Furthermore, simple diarization-derived behavioral features achieve performance comparable to Whisper-based speech embeddings for proficiency prediction, while combining both yields the best results. Importantly, both the speech and language use statistical analyses and language proficiency prediction performance remain largely preserved when using fully automatic diarization outputs, demonstrating the potential of respondent-centric conversational analysis for scalable language proficiency assessment.
This work systematically evaluates edge-oriented ASR-LLM pipelines for individuals with language impairments using comparison studies and ablation experiments across aphasia, child language impairment, and dementia datasets to identify transcript errors, repetition, noise, and input length as factors affecting system p...
A native-reference phone-class geometry for measuring second language (L2) pronunciation deviation without requiring pronunciation labels, read-aloud prompts, or matched recordings from native and L2 speakers is proposed.
Tina Raissi, Nhan Phan, Chen-Xi Wang et al.· arXiv.org· 0 citations
It is shown that strengthening the model's ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing.
Maureen de Seyssel, Jie Chi, Zakaria Aldeneh· arXiv.org· 0 citations
Claims about the grammatical competence of multilingual language models vary sharply with how competence is measured, yet the interaction between evaluation paradigm, post-training, and language resource availability has not been systematically examined. We evaluate base and post-trained models from six families on Mul...
Zhan-Yu Chen, Jaap Jumelet· Proceedings of the 2026 Conf...· 0 citations
The findings support the Multidomain Linguistic Difficulty Computational Screening Model (MLD-CSM) as a reliable and scalable framework for identifying learners who may require further language and communication assessment, particularly in multilingual educational settings with limited specialist resources.
Uzma Khan· Journal of Machine Learning...· 0 citations
: This study investigates the role of native language (L1) transfer in English language acquisition among Chinese learners, employing a questionnaire–based survey of 329 participants across different proficiency levels. The findings indicate that L1 influence operates across multiple domains, with the most substantial...
Jian Zhong· Proceeding in Humanities, Ed...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.