Search Results for author:
Found 4 papers, 1 papers with code
A Treatise On FST Lattice Based MMI Training
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models.
AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
For research community, we hope that AISHELL-2 corpus can be a solid resource for topics like transfer learning and robust ASR.
AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
An open-source Mandarin speech corpus called AISHELL-1 is released.
Purely sequence-trained neural networks for ASR based on lattice-free MMI
Models trained with LFMMI provide a relative word error rate reduction of ∼11. 5%, over those trained with cross-entropy objective function, and ∼8%, over those trained with cross-entropy and sMBR objective functions.
Ranked #4 on
Speech Recognition
on WSJ eval92
