Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition. (arXiv:2207.00857v1 [cs.SD])

Incorporating biasing words obtained as contextual knowledge is critical for
many automatic speech recognition (ASR) applications. This paper proposes the
use of graph neural network (GNN) encodings in a tree-constrained pointer
generator (TCPGen) component for end-to-end contextual ASR. By encoding the
biasing words in the prefix-tree with a tree-based GNN, lookahead for future
wordpieces in end-to-end ASR decoding is achieved at each tree node by
incorporating information about all wordpieces on the tree branches rooted from
it, which allows a …

arxiv generator graph graph neural network network neural network speech speech recognition tree