Training an ASR language model with a mix of unidirectional, bidirectional masked, and corrupted-context objectives yields lower word error rates across shallow fusion and n-best rescoring than unidirectional training alone.
In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems
Training an ASR language model with a mix of unidirectional, bidirectional masked, and corrupted-context objectives yields lower word error rates across shallow fusion and n-best rescoring than unidirectional training alone.