Skip to content

Commit 548fd3a

Browse files
committed
added references
1 parent 4e72542 commit 548fd3a

File tree

1 file changed

+12
-8
lines changed

1 file changed

+12
-8
lines changed

README.md

Lines changed: 12 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -44,11 +44,11 @@ BEST PATH GPU : "the fak friend of the fomly hae tC"
4444
* Token Passing: searches for most probable word sequence. The words are constrained to those contained in a dictionary. Can be extended to use a word-level LM. File: `TokenPassing.py` \[1\]
4545
* Lexicon Search: computes approximation with best path decoding to find similar words in dictionary. Returns the one with highest score. File: `LexiconSearch.py` \[3\]
4646
* Loss: calculates probability and loss of a given text in the RNN output. File: `Loss.py` \[1\] \[6\]
47-
* Word Beam Search: TensorFlow implementation see repository [CTCWordBeamSearch](https://github.com/githubharald/CTCWordBeamSearch)
47+
* Word Beam Search: TensorFlow implementation see repository [CTCWordBeamSearch](https://github.com/githubharald/CTCWordBeamSearch) \[8\]
4848

4949

5050
## Choosing the right algorithm
51-
[This paper](./doc/comparison.pdf) compares beam search decoding and token passing.
51+
[This paper](./doc/comparison.pdf) \[7\] compares beam search decoding and token passing.
5252
It gives suggestions when to use best path decoding, beam search decoding and token passing.
5353

5454

@@ -101,14 +101,18 @@ A GPU implementation is provided for best path decoding which requires pyopencl
101101

102102
## References
103103

104-
\[1\] Graves - Supervised sequence labelling with recurrent neural networks
104+
\[1\] [Graves - Supervised sequence labelling with recurrent neural networks](https://www.cs.toronto.edu/~graves/preprint.pdf)
105105

106-
\[2\] Hwang - Character-level incremental speech recognition with recurrent neural networks
106+
\[2\] [Hwang - Character-level incremental speech recognition with recurrent neural networks](https://arxiv.org/pdf/1601.06581.pdf)
107107

108-
\[3\] Shi - An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition: https://github.com/bgshih/crnn
108+
\[3\] [Shi - An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://arxiv.org/pdf/1507.05717.pdf)
109109

110-
\[4\] Marti - The IAM-database: an English sentence database for offline handwriting recognition: http://www.fki.inf.unibe.ch/databases/iam-handwriting-database
110+
\[4\] [Marti - The IAM-database: an English sentence database for offline handwriting recognition](http://www.fki.inf.unibe.ch/databases/iam-handwriting-database)
111111

112-
\[5\] Beam Search Decoding in CTC-trained Neural Networks: https://towardsdatascience.com/5a889a3d85a7
112+
\[5\] [Beam Search Decoding in CTC-trained Neural Networks](https://towardsdatascience.com/5a889a3d85a7)
113113

114-
\[6\] An Intuitive Explanation of Connectionist Temporal Classification: https://towardsdatascience.com/3797e43a86c
114+
\[6\] [An Intuitive Explanation of Connectionist Temporal Classification](https://towardsdatascience.com/3797e43a86c)
115+
116+
\[7\] [Scheidl - Comparison of Connectionist Temporal Classification Decoding Algorithms](./doc/comparison.pdf)
117+
118+
\[8\] [Scheidl - Word Beam Search: A Connectionist Temporal Classification Decoding Algorithm](https://repositum.tuwien.ac.at/obvutwoa/download/pdf/2774578)

0 commit comments

Comments
 (0)
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy