Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator. (arXiv:2205.09058v1 [cs.CL])

Contextual knowledge is essential for reducing speech recognition errors on
high-valued long-tail words. This paper proposes a novel tree-constrained
pointer generator (TCPGen) component that enables end-to-end ASR models to bias
towards a list of long-tail words obtained using external contextual
information. With only a small overhead in memory use and computation cost,
TCPGen can structure thousands of biasing words efficiently into a symbolic
prefix-tree and creates a neural shortcut between the tree and the final ASR
output to facilitate the …

arxiv asr errors generator tree