DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning
Speech recognition technology has played an indispensable role in realizing human-computer intelligent interaction. However, most of the current Chinese speech recognition systems are provided online or offline models with low accuracy and poor performance. To improve the performance of offline Chin...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2022/6927400 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553519607971840 |
|---|---|
| author | Hong Lei Yue Xiao Yanchun Liang Dalin Li Heow Pueh Lee |
| author_facet | Hong Lei Yue Xiao Yanchun Liang Dalin Li Heow Pueh Lee |
| author_sort | Hong Lei |
| collection | DOAJ |
| description | Speech recognition technology has played an indispensable role in realizing human-computer intelligent interaction. However, most of the current Chinese speech recognition systems are provided online or offline models with low accuracy and poor performance. To improve the performance of offline Chinese speech recognition, we propose a hybrid acoustic model of deep convolutional neural network, long short-term memory, and deep neural network (DCNN-LSTM-DNN, DLD). This model utilizes DCNN to reduce frequency variation and adds a batch normalization (BN) layer after its convolutional layer to ensure the stability of data distribution, and then use LSTM to effectively solve the gradient vanishing problem. Finally, the fully connected structure of DNN is utilized to efficiently map the input features into a separable space, which is helpful for data classification. Therefore, leveraging the strengths of DCNN, LSTM, and DNN by combining them into a unified architecture can effectively improve speech recognition performance. Our model was tested on the open Chinese speech database THCHS-30 released by the Center for Speech and Language Technology (CSLT) of Tsinghua University, and it was concluded that the DLD model with 3 layers of LSTM and 3 layers of DNN had the best performance, reaching 13.49% of words error rate (WER). |
| format | Article |
| id | doaj-art-0d77ef54025b452b90126f22ba7c8436 |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-0d77ef54025b452b90126f22ba7c84362025-02-03T05:53:49ZengWileyComplexity1099-05262022-01-01202210.1155/2022/6927400DLD: An Optimized Chinese Speech Recognition Model Based on Deep LearningHong Lei0Yue Xiao1Yanchun Liang2Dalin Li3Heow Pueh Lee4Faculty of Data ScienceZhuhai Laboratory of Key Laboratory for Symbol Computation and Knowledge Engineering of Ministry of EducationZhuhai Laboratory of Key Laboratory for Symbol Computation and Knowledge Engineering of Ministry of EducationZhuhai Laboratory of Key Laboratory for Symbol Computation and Knowledge Engineering of Ministry of EducationDepartment of Mechanical EngineeringSpeech recognition technology has played an indispensable role in realizing human-computer intelligent interaction. However, most of the current Chinese speech recognition systems are provided online or offline models with low accuracy and poor performance. To improve the performance of offline Chinese speech recognition, we propose a hybrid acoustic model of deep convolutional neural network, long short-term memory, and deep neural network (DCNN-LSTM-DNN, DLD). This model utilizes DCNN to reduce frequency variation and adds a batch normalization (BN) layer after its convolutional layer to ensure the stability of data distribution, and then use LSTM to effectively solve the gradient vanishing problem. Finally, the fully connected structure of DNN is utilized to efficiently map the input features into a separable space, which is helpful for data classification. Therefore, leveraging the strengths of DCNN, LSTM, and DNN by combining them into a unified architecture can effectively improve speech recognition performance. Our model was tested on the open Chinese speech database THCHS-30 released by the Center for Speech and Language Technology (CSLT) of Tsinghua University, and it was concluded that the DLD model with 3 layers of LSTM and 3 layers of DNN had the best performance, reaching 13.49% of words error rate (WER).http://dx.doi.org/10.1155/2022/6927400 |
| spellingShingle | Hong Lei Yue Xiao Yanchun Liang Dalin Li Heow Pueh Lee DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning Complexity |
| title | DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning |
| title_full | DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning |
| title_fullStr | DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning |
| title_full_unstemmed | DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning |
| title_short | DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning |
| title_sort | dld an optimized chinese speech recognition model based on deep learning |
| url | http://dx.doi.org/10.1155/2022/6927400 |
| work_keys_str_mv | AT honglei dldanoptimizedchinesespeechrecognitionmodelbasedondeeplearning AT yuexiao dldanoptimizedchinesespeechrecognitionmodelbasedondeeplearning AT yanchunliang dldanoptimizedchinesespeechrecognitionmodelbasedondeeplearning AT dalinli dldanoptimizedchinesespeechrecognitionmodelbasedondeeplearning AT heowpuehlee dldanoptimizedchinesespeechrecognitionmodelbasedondeeplearning |