Transformer-based language modeling and decoding for conversational speech recognition
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WBLDWELWrecord.jsonopen to challenge →
classification
cs.CL
cs.LGeess.AS
keywords
languageconversationaldecodingmodelrecognitionspeechtransformer-basedability
read the original abstract
We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to lattice re-scoring that allows for longer range history captured by a transfomer-based language model and takes advantage of a transformer's ability to avoid computing sequentially.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.