Word Beam Search: A Connectionist Temporal Classification Decoding Algorithm

Scheidl, Harald; Fiel, Stefan; Sablatnig, Robert

doi:10.1109/icfhr-2018.2018.00052

Cited by 77 publications

(82 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the segmented words are feeded into the model. Word Beam Search method is used [13]. From the result, we have achieve 62.85 % accuracy in recognizing the characters.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Mechanism for Offline Character Recognition

Khan¹

2019

IJRASET

View full text Add to dashboard Cite

Character recognition is an exciting and interesting computer vision research field due to distinct human handwriting and can be adapted to recognize characters. Several upgrades to analyze handwritten data have been made, still data cannot be analyzed with 100% accuracy by the system. In order to improve the accuracy, we propose a method to recognize the characters of English language. This proposal is limited to English characters only. In our proposal, a Convolutional Neural Network (CNN) based on TensorFlow, an open source library for building machine intelligence applications, is designed for character recognition. Experimental outcomes demonstrate that the proposed model has finer accuracy and models are deployed quickly and easily.

show abstract

“…Finally, the segmented words are feeded into the model. Word Beam Search method is used [13]. From the result, we have achieve 62.85 % accuracy in recognizing the characters.…”

Section: Discussionmentioning

confidence: 99%

“…The word beam search method [13] is used to mapped the input sequence to the output sequence. The resulting ouput sequence is the required output image after decoding.…”

Section: E Decodingmentioning

confidence: 99%

A Mechanism for Offline Character Recognition

Khan¹

2019

IJRASET

View full text Add to dashboard Cite

show abstract

“…The WBS decoder is placed just following the CTC layers for output decoding. The main advantages of the WBS decoder [44] over token passing decoder are:…”

Section: E Word Beam Search (Wbs) Decodermentioning

confidence: 99%

Exploring Deep Learning Approaches to Recognize Handwritten Arabic Texts

2020

View full text Add to dashboard Cite

Recognition of cursive handwritten Arabic text is a difficult problem because of contextsensitive character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. In this paper, we review and investigate different deep learning architectures and modeling choices for Arabic handwriting recognition. Further, we address the problem that imbalanced data sets present to deep learning systems. In order to address this issue, we are presenting a novel adaptive data-augmentation algorithm to promote class diversity. This algorithm assigns a weight to each word in the database lexicon. This weight is calculated based on the average probability of each class in a word. Experimental results on the IFN/ENIT and AHDB databases have shown that our presented approach yields state-of-the-art results. INDEX TERMS Arabic handwriting recognition (AHR), deep learning neural network (DLNN), convolutional neural networks (CNN), connectionist temporal classification (CTC), recurrent neural network (RNN), IFN/ENIT database, long short-term memory (LSTM), bi-directional long short-term memory (BLSTM), word beam search (WBS).

show abstract

“…We referred to the independent labelling of each time step, or frame. Figure 2 depicts the best path decoding example [26,27] for a 1 s audio file.…”

Section: Phoneme Recognition and Time Alignmentmentioning

confidence: 99%

“…We referred to the independent labelling of each time step, or frame. Figure 2 depicts the best path decoding example [26,27] for a 1 s audio file. ch + sh 0.00 … 0.00 0.00 0.00 0.00 … 0.09 0.00 0.00 0.00 … 0.00 d + d' 0.00 … 0.21 0.10 0.00 0.00 … 0.00 0.00 0.00 0.00 … 0.00 g + g' 0.00 … 0.65 0.88 1.00 1.00 … 0.00 0.00 0.00 0.00 … 0.00 k + k' 0.00 … 0.00 0.00 0.00 0.00 … 0.00 0.00 0.00 0.00 … 0.00 pause 1.00 … 0.00 0.00 0.00 0.00 … 0.13 0.01 0.01 0.00 … 1.00 s + s' 0.00 … 0.00 0.00 0.00 0.00 … 0.78 0.99 0.99 1.00 … 0.00 t + t' 0.00 … 0.00 0.00 0.00 0.00 … 0.00 0.00 0.00 0.00 … 0.00 vow 0.00 … 0.14 0.02 0.00 0.00 … 0.00 0.00 0.00 0.00 … 0.00 As a result, we obtained a sequence of labels.…”

Section: Phoneme Recognition and Time Alignmentunclassified

Evaluation of Speech Quality Through Recognition and Classification of Phonemes

2019

View full text Add to dashboard Cite

This paper discusses an approach for assessing the quality of speech while undergoing speech rehabilitation. One of the main reasons for speech quality decrease during the surgical treatment of vocal tract diseases is the loss of the vocal tractˈs parts and the disruption of its symmetry. In particular, one of the most common oncological diseases of the oral cavity is cancer of the tongue. During surgical treatment, a glossectomy is performed, which leads to the need for speech rehabilitation to eliminate the occurring speech defects, leading to a decrease in speech intelligibility. In this paper, we present an automated approach for conducting the speech quality evaluation. The approach relies on a convolutional neural network (CNN). The main idea of the approach is to train an individual neural network for a patient before having an operation to recognize typical sounding of phonemes for their speech. The neural network will thereby be able to evaluate the similarity between the patientˈs speech before and after the surgery. The recognition based on the full phoneme set and the recognition by groups of phonemes were considered. The correspondence of assessments obtained through the autorecognition approach with those from the human-based approach is shown. The automated approach is principally applicable to defining boundaries between phonemes. The paper shows that iterative training of the neural network and continuous updating of the training dataset gradually improve the ability of the CNN to define boundaries between different phonemes.

show abstract

Word Beam Search: A Connectionist Temporal Classification Decoding Algorithm

Cited by 77 publications

References 10 publications

A Mechanism for Offline Character Recognition

A Mechanism for Offline Character Recognition

Exploring Deep Learning Approaches to Recognize Handwritten Arabic Texts

Evaluation of Speech Quality Through Recognition and Classification of Phonemes

Contact Info

Product

Resources

About