Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method
The concept of Deep learning is a part of machine learning which is very useful nowadays to achieve accurate voice and speech recognition based on the training data by creating robust algorithms. It is also possible to separate the noise from original speech as well as the separation of tracks in pa...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10298228/ |
| _version_ | 1797635402947887104 |
|---|---|
| author | S. V. Aswin Kumer Lakshmi Bharath Gogu E. Mohan Suman Maloji Balaji Natarajan G. Sambasivam Vaibhav Bhushan Tyagi |
| author_facet | S. V. Aswin Kumer Lakshmi Bharath Gogu E. Mohan Suman Maloji Balaji Natarajan G. Sambasivam Vaibhav Bhushan Tyagi |
| author_sort | S. V. Aswin Kumer |
| collection | DOAJ |
| description | The concept of Deep learning is a part of machine learning which is very useful nowadays to achieve accurate voice and speech recognition based on the training data by creating robust algorithms. It is also possible to separate the noise from original speech as well as the separation of tracks in particular audio signal with the help of machine learning algorithms. In this paper, the implementation is applicable for voice assistant to separate the tracks and the noises from the multiple original audio which reproduces simultaneously using the speech enhancement and universal code book. For that, the Hybrid Deep Learning Algorithm has been developed and the training data sets are also created and achieve the accuracy in the speech recognition for the variety of voice assistants. Most of the time, the voice assistant recognizes the voice with noises and musical audio which results in the malfunction of devices which can be controlled by the same voice assistant. The Generative adversarial networks from Deep learning and the blind source separation method from multi-channel model are combined to form this proposed hybrid deep learning model. |
| first_indexed | 2024-03-11T12:20:37Z |
| format | Article |
| id | doaj.art-3c25bb040f0f4d46ad7f25b6076abea8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T12:20:37Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3c25bb040f0f4d46ad7f25b6076abea82023-11-07T00:03:00ZengIEEEIEEE Access2169-35362023-01-011112070712072010.1109/ACCESS.2023.332820810298228Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning MethodS. V. Aswin Kumer0https://orcid.org/0000-0002-0511-3085Lakshmi Bharath Gogu1E. Mohan2https://orcid.org/0000-0001-7362-6993Suman Maloji3Balaji Natarajan4https://orcid.org/0000-0003-0040-9271G. Sambasivam5https://orcid.org/0000-0002-7407-4796Vaibhav Bhushan Tyagi6https://orcid.org/0000-0001-8153-3607Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, IndiaDepartment of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, IndiaDepartment of ECE, Saveetha School of Engineering, SIMATS, Chennai, Tamil Nadu, IndiaDepartment of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Sri Venkateshwaraa College of Engineering and Technology, Ariyur, Puducherry, IndiaSchool of Computing and Data Science, Xiamen University Malaysia, Sepang, Selangor, MalaysiaFaculty of Engineering, ISBAT University, Kampala, UgandaThe concept of Deep learning is a part of machine learning which is very useful nowadays to achieve accurate voice and speech recognition based on the training data by creating robust algorithms. It is also possible to separate the noise from original speech as well as the separation of tracks in particular audio signal with the help of machine learning algorithms. In this paper, the implementation is applicable for voice assistant to separate the tracks and the noises from the multiple original audio which reproduces simultaneously using the speech enhancement and universal code book. For that, the Hybrid Deep Learning Algorithm has been developed and the training data sets are also created and achieve the accuracy in the speech recognition for the variety of voice assistants. Most of the time, the voice assistant recognizes the voice with noises and musical audio which results in the malfunction of devices which can be controlled by the same voice assistant. The Generative adversarial networks from Deep learning and the blind source separation method from multi-channel model are combined to form this proposed hybrid deep learning model.https://ieeexplore.ieee.org/document/10298228/Blind source separation (BSS) methoddeep learning methodgenerative adversarial networks (GAN)multi-channel methodnoise separationspeech recognition |
| spellingShingle | S. V. Aswin Kumer Lakshmi Bharath Gogu E. Mohan Suman Maloji Balaji Natarajan G. Sambasivam Vaibhav Bhushan Tyagi Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method IEEE Access Blind source separation (BSS) method deep learning method generative adversarial networks (GAN) multi-channel method noise separation speech recognition |
| title | Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method |
| title_full | Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method |
| title_fullStr | Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method |
| title_full_unstemmed | Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method |
| title_short | Track and Noise Separation Based on the Universal Codebook and Enhanced Speech Recognition Using Hybrid Deep Learning Method |
| title_sort | track and noise separation based on the universal codebook and enhanced speech recognition using hybrid deep learning method |
| topic | Blind source separation (BSS) method deep learning method generative adversarial networks (GAN) multi-channel method noise separation speech recognition |
| url | https://ieeexplore.ieee.org/document/10298228/ |
| work_keys_str_mv | AT svaswinkumer trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT lakshmibharathgogu trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT emohan trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT sumanmaloji trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT balajinatarajan trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT gsambasivam trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod AT vaibhavbhushantyagi trackandnoiseseparationbasedontheuniversalcodebookandenhancedspeechrecognitionusinghybriddeeplearningmethod |