This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the "compact-CTC", in which direct transitions between units are replaced with <epsilon> back-off transitions; (2) the "minimal-CTC", that only adds <blank> self-loops when used in WFST-composition; and (3) the "selfless-CTC" variants, which disallows self-loop for non-blank units. Compact-CTC allows for 1.5 times smaller WFST decoding graphs and reduces memory consumption by two times when training CTC models with the LF-MMI objective without hurting the recognition accuracy. Minimal-CTC reduces graph size and memory consumption by two and four times for the cost of a small accuracy drop. Using selfless-CTC can improve the accuracy for wide context window models.
@article{arxiv.2110.03098,
title = {CTC Variations Through New WFST Topologies},
author = {Aleksandr Laptev and Somshubra Majumdar and Boris Ginsburg},
journal= {arXiv preprint arXiv:2110.03098},
year = {2022}
}
Comments
Accepted to Interspeech 2022, 5 pages, 2 figures, 7 tables