Papers
arxiv:2305.11539

Delay-penalized CTC implemented based on Finite State Transducer

Published on May 19, 2023
Authors:
,
,
,
,
,
,

Abstract

Connectionist Temporal Classification (CTC) suffers from the latency problem when applied to streaming models. We argue that in CTC lattice, the alignments that can access more future context are preferred during training, thereby leading to higher symbol delay. In this work we propose the delay-penalized CTC which is augmented with latency penalty regularization. We devise a flexible and efficient implementation based on the differentiable Finite State Transducer (FST). Specifically, by attaching a binary attribute to CTC topology, we can locate the frames that firstly emit non-blank tokens on the resulting CTC lattice, and add the frame offsets to the log-probabilities. Experimental results demonstrate the effectiveness of our proposed delay-penalized CTC, which is able to balance the delay-accuracy trade-off. Furthermore, combining the delay-penalized transducer enables the CTC model to achieve better performance and lower latency. Our work is open-sourced and publicly available https://github.com/k2-fsa/k2.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2305.11539 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2305.11539 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2305.11539 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.