2 papers
cs.CL2025
PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation
Jiajun He, Naoki Sawada, Koichi Miyazaki +1
Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-…
eess.AS2025
CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
Jiajun He, Naoki Sawada, Koichi Miyazaki +1
In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditio…