A Hardware-Oriented and Memory-Efficient Method for CTC Decoding release_df44erzet5fktj6fs3goreh4ze

by Siyuan Lu, Jinming Lu, Jun Lin, Zhongfeng Wang

Released as a article .

2019  

Abstract

The Connectionist Temporal Classification (CTC) has achieved great success in sequence to sequence analysis tasks such as automatic speech recognition (ASR) and scene text recognition (STR). These applications can use the CTC objective function to train the recurrent neural networks (RNNs), and decode the outputs of RNNs during inference. While hardware architectures for RNNs have been studied, hardware-based CTCdecoders are desired for high-speed CTC-based inference systems. This paper, for the first time, provides a low-complexity and memory-efficient approach to build a CTC-decoder based on the beam search decoding. Firstly, we improve the beam search decoding algorithm to save the storage space. Secondly, we compress a dictionary (reduced from 26.02MB to 1.12MB) and use it as the language model. Meanwhile searching this dictionary is trivial. Finally, a fixed-point CTC-decoder for an English ASR and an STR task using the proposed method is implemented with C++ language. It is shown that the proposed method has little precision loss compared with its floating-point counterpart. Our experiments demonstrate the compression ratio of the storage required by the proposed beam search decoding algorithm are 29.49 (ASR) and 17.95 (STR).
In text/plain format

Archived Files and Locations

application/pdf  2.2 MB
file_lvg3pvug2vaudkw4aztf22rgoa
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-05-08
Version   v1
Language   en ?
arXiv  1905.03175v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ad885165-4e2d-4d2c-bdff-daf0de65bff3
API URL: JSON