Pith. sign in

REVIEW

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.05081 v1 pith:4KD5WQHL submitted 2021-03-08 eess.AS cs.CLcs.SD

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

classification eess.AS cs.CLcs.SD
keywords latticerescoringneuralparallelstrategyalgorithmexpandedexpansion
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition. First, lattices from first-pass decoding are expanded by the proposed posterior-based lattice expansion algorithm. Second, each expanded lattice is converted into a minimal list of hypotheses that covers every arc. Each hypothesis is constrained to be the best path for at least one arc it includes. For each lattice, the neural LM scores of the minimal list are computed in parallel and are then integrated back to the lattice in the rescoring stage. Experiments on the Switchboard dataset show that the proposed rescoring strategy obtains comparable recognition performance and generates more compact lattices than a competitive baseline method. Furthermore, the parallel rescoring method offers more flexibility by simplifying the integration of PyTorch-trained neural LMs for lattice rescoring with Kaldi.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.