Abstract | ||
---|---|---|
Hybrid deep neural network hidden Markov models (DNN-HMM) have achieved impressive results on large vocabulary continuous speech recognition (LVCSR) tasks. However, the recent approaches using DNN-HMM models are not explored much for text recognition. Inspired by the current work in automatic speech recognition (ASR) and machine translation, we present an open vocabulary sub-word text recognition system. The sub-word lexicon and sub-word language model (LM) helps in overcoming the challenge of recognizing out of vocabulary (OOV) words, and a time delay neural network (TDNN) and convolution neural network (CNN) based DNN-HMM optical model (OM) efficiently models the sequence dependency in the line image. We present results on 12 datasets with training data varying from 6k lines to 600k lines. The system is built for 8 languages, i.e., English, French, Arabic, Chinese, Farsi, Tamil, Russian, and Korean. We report competitive results on several commonly used handwritten and printed text datasets. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICDAR.2019.00111 | ICDAR |
Field | DocType | Citations |
Pattern recognition,Convolutional neural network,Computer science,Machine translation,Speech recognition,Time delay neural network,Lexicon,Artificial intelligence,Artificial neural network,Hidden Markov model,Vocabulary,Language model | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 14 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ashish Arora | 1 | 0 | 0.34 |
Paola García | 2 | 3 | 4.47 |
Shinji Watanabe | 3 | 1158 | 139.38 |
Vimal Manohar | 4 | 54 | 7.99 |
Yiwen Shao | 5 | 0 | 1.01 |
Sanjeev Khudanpur | 6 | 2155 | 202.00 |
Chun-Chieh Chang | 7 | 0 | 0.34 |
Babak Rekabdar | 8 | 0 | 0.34 |
Bagher BabaAli | 9 | 88 | 7.64 |
Daniel Povey | 10 | 2442 | 231.75 |
David Etter | 11 | 0 | 1.01 |
Desh Raj | 12 | 0 | 2.37 |
Hossein Hadian | 13 | 11 | 3.31 |
Jan Trmal | 14 | 235 | 20.91 |