A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training
Computer-assisted pronunciation training (CAPT) is a helpful method for self-directed or long-distance foreign language learning. It greatly benefits from the progress, and of acoustic signal processing and artificial intelligence techniques. However, in real-life applications, embedded solutions ar...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/10/5835 |
| _version_ | 1797601294889779200 |
|---|---|
| author | Yanjing Bi Chao Li Yannick Benezeth Fan Yang |
| author_facet | Yanjing Bi Chao Li Yannick Benezeth Fan Yang |
| author_sort | Yanjing Bi |
| collection | DOAJ |
| description | Computer-assisted pronunciation training (CAPT) is a helpful method for self-directed or long-distance foreign language learning. It greatly benefits from the progress, and of acoustic signal processing and artificial intelligence techniques. However, in real-life applications, embedded solutions are usually desired. This paper conceives a register-transfer level (RTL) core to facilitate the pronunciation diagnostic tasks by suppressing the mulitcollinearity of the speech waveforms. A recently proposed heterogeneous machine learning framework is selected as the French phoneme pronunciation diagnostic algorithm. This RTL core is implemented and optimized within a very-high-level synthesis method for fast prototyping. An original French phoneme data set containing 4830 samples is used for the evaluation experiments. The experiment results demonstrate that the proposed implementation reduces the diagnostic error rate by 0.79–1.33% compared to the state-of-the-art and achieves a speedup of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>10.89</mn><mo>×</mo></mrow></semantics></math></inline-formula> relative to its CPU implementation at the same abstract level of programming languages. |
| first_indexed | 2024-03-11T04:00:00Z |
| format | Article |
| id | doaj.art-e7d2d4bf4f5346ddae5c46643816d796 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T04:00:00Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e7d2d4bf4f5346ddae5c46643816d7962023-11-18T00:16:23ZengMDPI AGApplied Sciences2076-34172023-05-011310583510.3390/app13105835A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation TrainingYanjing Bi0Chao Li1Yannick Benezeth2Fan Yang3School of Foreign Studies, Capital University of Economics and Business, Beijing 100070, ChinaState Key Laboratory of Acoustics, Institute of Acoustics, Beijing 100190, ChinaLaboratory of ImViA, University of Burgundy-Franche-Comté, 21078 Dijon, FranceLaboratory of ImViA, University of Burgundy-Franche-Comté, 21078 Dijon, FranceComputer-assisted pronunciation training (CAPT) is a helpful method for self-directed or long-distance foreign language learning. It greatly benefits from the progress, and of acoustic signal processing and artificial intelligence techniques. However, in real-life applications, embedded solutions are usually desired. This paper conceives a register-transfer level (RTL) core to facilitate the pronunciation diagnostic tasks by suppressing the mulitcollinearity of the speech waveforms. A recently proposed heterogeneous machine learning framework is selected as the French phoneme pronunciation diagnostic algorithm. This RTL core is implemented and optimized within a very-high-level synthesis method for fast prototyping. An original French phoneme data set containing 4830 samples is used for the evaluation experiments. The experiment results demonstrate that the proposed implementation reduces the diagnostic error rate by 0.79–1.33% compared to the state-of-the-art and achieves a speedup of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>10.89</mn><mo>×</mo></mrow></semantics></math></inline-formula> relative to its CPU implementation at the same abstract level of programming languages.https://www.mdpi.com/2076-3417/13/10/5835computer-assisted pronunciation traininghigh-level synthesisembedded designsmachine learningFPGA |
| spellingShingle | Yanjing Bi Chao Li Yannick Benezeth Fan Yang A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training Applied Sciences computer-assisted pronunciation training high-level synthesis embedded designs machine learning FPGA |
| title | A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training |
| title_full | A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training |
| title_fullStr | A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training |
| title_full_unstemmed | A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training |
| title_short | A RTL Implementation of Heterogeneous Machine Learning Network for French Computer Assisted Pronunciation Training |
| title_sort | rtl implementation of heterogeneous machine learning network for french computer assisted pronunciation training |
| topic | computer-assisted pronunciation training high-level synthesis embedded designs machine learning FPGA |
| url | https://www.mdpi.com/2076-3417/13/10/5835 |
| work_keys_str_mv | AT yanjingbi artlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT chaoli artlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT yannickbenezeth artlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT fanyang artlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT yanjingbi rtlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT chaoli rtlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT yannickbenezeth rtlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining AT fanyang rtlimplementationofheterogeneousmachinelearningnetworkforfrenchcomputerassistedpronunciationtraining |