Results 161 to 170 of about 76,886 (181)

End-to-end keywords spotting based on connectionist temporal classification for Mandarin

2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2016
Traditional hybrid DNN-HMM based ASR system for keywords spotting which models HMM states are not flexible to optimize for a specific language. In this paper, we construct an end-to-end acoustic model based ASR for keywords spotting in Mandarin.
Ye Bai, Jiangyan Yi, Hao Ni, Zhengqi Wen, Bin Liu 0041, Ya Li 0001, Jianhua Tao 0001   +6 more
openaire   +1 more source

Tigrinya End-to-End Speech Recognition: A Hybrid Connectionist Temporal Classification-Attention Approach

PanAfriCon AI, 2023
Bereket Desbele Ghebregiorgis, Yonatan Yosef Tekle, Mebrahtu Fisshaye Kidane, Mussie Kaleab Keleta, Rutta Fissehatsion Ghebraeb, Daniel Tesfai Gebretatios   +5 more
openaire   +2 more sources

Character Recognition Operations of a Connectionist Temporal Classification in Neural Network

2019 International Conference on Smart Systems and Inventive Technology (ICSSIT), 2019
Neural network plays a major role in recognizing the character from image text lines, usually consist of convolutional neural network (CNN), which performs to extract characters from the text lines of image and Recurrent Neural Network to propagate the sequence of information to neural network. Connectionist temporal classification can handle vanishing
Pinagadi Venkateswararao, S. Murugavalli
openaire   +1 more source

Applying connectionist temporal classification objective function to Chinese Mandarin speech recognition

2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2016
In automatic speech recognition (ASR), connectionist temporal classification (CTC) is regarded as a method to achieve end-to-end system. Actually, not only characters (Chars) but also context independent phonemes (CI-Phns) or context dependent phoneme (CD-Phns) can be used as output units of CTC-trained neural network.
Pengrui Wang, Jie Li 0032, Bo Xu 0002
openaire   +1 more source

Practical Connectionist Temporal Classification for accurate and efficient training

2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022
openaire   +1 more source

Visual speech recognition based on connectionist temporal classification loss

2023
JIN SHIWEI, LEE JONG, WNUK MATTHEW, COSTELA FRANCISCO   +3 more
openaire   +2 more sources

Connectionist Temporal Modeling for Weakly Supervised Action Labeling

Lecture Notes in Computer Science, 2016
Juan CARLOS Niebles, De-An Huang, Li Fei-Fei   +2 more
exaly  

An Innovative Method to analyze the Accuracy and Prediction rate of Handwritten Digit Recognition with Dimensionality Reduction Algorithm by comparing with Connectionist Temporal Classification

2022
K Malathi
exaly  

Efficient connectionist temporal classification for binary classification

2020
KASKARI SAEED MOSAYYEBPOUR, THORMUNDSSON TRAUSTI, NESTA FRANCESCO   +2 more
openaire   +1 more source

The Effect of Different Optimization Techniques on End-to-End Turkish Speech Recognition Systems that use Connectionist Temporal Classification

2018
Recep Sinan Arslan
exaly