1. L
umos
: Empowering Multimodal LLMs with Scene Text Recognition;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24
2. Cross Modal Training for ASR Error Correction with Contrastive Learning;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
3. ED-CEC: Improving Rare word Recognition Using ASR Postprocessing Based on Error Detection and Context-Aware Error Correction;2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU);2023-12-16
4. Dictionary-driven Chinese ASR Entity Correction with Controllable Decoding;2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC);2023-10-31
5. Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems;Interspeech 2022;2022-09-18