COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM
This paper evaluates and compares the performances of three well-known optimization algorithms (Adagrad, Adam, Momentum) for faster training the neural network of CTC algorithm for speech recognition. For CTC algorithms recurrent neural network has been used, specifically Long-Short-Term memory. LST...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Lublin University of Technology
2019-09-01
|
| Series: | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| Subjects: | |
| Online Access: | https://ph.pollub.pl/index.php/iapgos/article/view/234 |
| _version_ | 1818208512717619200 |
|---|---|
| author | Yedilkhan Amirgaliyev Kuanyshbay Kuanyshbay Aisultan Shoiynbek |
| author_facet | Yedilkhan Amirgaliyev Kuanyshbay Kuanyshbay Aisultan Shoiynbek |
| author_sort | Yedilkhan Amirgaliyev |
| collection | DOAJ |
| description | This paper evaluates and compares the performances of three well-known optimization algorithms (Adagrad, Adam, Momentum) for faster training the neural network of CTC algorithm for speech recognition. For CTC algorithms recurrent neural network has been used, specifically Long-Short-Term memory. LSTM is effective and often used model. Data has been downloaded from VCTK corpus of Edinburgh University. The results of optimization algorithms have been evaluated by the Label error rate and CTC loss. |
| first_indexed | 2024-12-12T04:46:00Z |
| format | Article |
| id | doaj.art-c4441d179662410ea0d882461431bed7 |
| institution | Directory Open Access Journal |
| issn | 2083-0157 2391-6761 |
| language | English |
| last_indexed | 2024-12-12T04:46:00Z |
| publishDate | 2019-09-01 |
| publisher | Lublin University of Technology |
| record_format | Article |
| series | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| spelling | doaj.art-c4441d179662410ea0d882461431bed72022-12-22T00:37:38ZengLublin University of TechnologyInformatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska2083-01572391-67612019-09-019310.35784/iapgos.234COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEMYedilkhan Amirgaliyev0Kuanyshbay Kuanyshbay1Aisultan Shoiynbek21 Institute Information and Computational Technologies CS MES RK, Almaty, Kazakhstan, 2 Suleyman Demirel University, Almaty, Kazakhstan1 Institute Information and Computational Technologies CS MES RK, Almaty, Kazakhstan, 2 Suleyman Demirel University, Almaty, Kazakhstan1 Institute Information and Computational Technologies CS MES RK, Almaty, Kazakhstan, 2 Suleyman Demirel University, Almaty, KazakhstanThis paper evaluates and compares the performances of three well-known optimization algorithms (Adagrad, Adam, Momentum) for faster training the neural network of CTC algorithm for speech recognition. For CTC algorithms recurrent neural network has been used, specifically Long-Short-Term memory. LSTM is effective and often used model. Data has been downloaded from VCTK corpus of Edinburgh University. The results of optimization algorithms have been evaluated by the Label error rate and CTC loss.https://ph.pollub.pl/index.php/iapgos/article/view/234recurrent neural networksearch methodsacousticsystems modeling language |
| spellingShingle | Yedilkhan Amirgaliyev Kuanyshbay Kuanyshbay Aisultan Shoiynbek COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska recurrent neural network search methods acoustic systems modeling language |
| title | COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM |
| title_full | COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM |
| title_fullStr | COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM |
| title_full_unstemmed | COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM |
| title_short | COMPARISON OF OPTIMIZATION ALGORITHMS OF CONNECTIONIST TEMPORAL CLASSIFIER FOR SPEECH RECOGNITION SYSTEM |
| title_sort | comparison of optimization algorithms of connectionist temporal classifier for speech recognition system |
| topic | recurrent neural network search methods acoustic systems modeling language |
| url | https://ph.pollub.pl/index.php/iapgos/article/view/234 |
| work_keys_str_mv | AT yedilkhanamirgaliyev comparisonofoptimizationalgorithmsofconnectionisttemporalclassifierforspeechrecognitionsystem AT kuanyshbaykuanyshbay comparisonofoptimizationalgorithmsofconnectionisttemporalclassifierforspeechrecognitionsystem AT aisultanshoiynbek comparisonofoptimizationalgorithmsofconnectionisttemporalclassifierforspeechrecognitionsystem |