Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments

Sara Papi, Peidong Wang, Junkun Chen, Jian Xue, Jinyu Li, Yashesh Gaur
January, 2023
Cite DOI Poster Video
Type
Conference paper
Publication
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
Training;Degradation;Transducers;Costs;Conferences;Speech enhancement;Transformers;automatic speech recognition;speech translation;streaming;serialized output training