An optimized approach to speech transcription using blind source separation and speech-to-text machine learning models

Research Article
Open access

An optimized approach to speech transcription using blind source separation and speech-to-text machine learning models

Chaoyang Yin 1*
  • 1 Grainger College of Engineering, University of Illinois at Urbana-Champaign, Champaign, Illinois, 61820, United States    
  • *corresponding author cyin9@illinois.edu
Published on 31 January 2024 | https://doi.org/10.54254/2755-2721/30/20230085
ACE Vol.30
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-83558-285-5
ISBN (Online): 978-1-83558-286-2

Abstract

The use of speech-to-text transcription has a multitude of applications in various industries, including accessibility support, language processing, and automatic subtitling. In recent years, there has been greater interest in incorporating automatic speech source separation features to improve the accuracy and efficiency of transcription mechanisms. This paper aims to design a transcription mechanism that utilizes DUET algorithm to separate speech sources in a stereo setup. The separated sources are then transcribed into text using a machine learning model. The study evaluates the effectiveness of this approach using a dataset of speech recordings. The results of the study indicate high accuracy in speech separation and transcription, highlighting the potential of this approach for practical applications. However, the study also revealed potential issues with the mechanism, indicating the need for further exploration and refinement. These findings indicate the potential of the proposed approach for practical applications, and propose insight for further development and researches in this area.

Keywords:

audio processing, blind source separation, speech recognition

Yin,C. (2024). An optimized approach to speech transcription using blind source separation and speech-to-text machine learning models. Applied and Computational Engineering,30,131-138.
Export citation

References

[1]. Li Y and Wang D 2021 Noise-Robust Text-Dependent Speaker Verification based on Deep Neural Networks IEEE Access 9 p 1-11

[2]. Chen J and Wang D 2018 Speaker-Independent Speech Recognition System for Multi-Speaker Scenarios using Convolutional Neural Networks IEEE Access 6 p 78317-78324

[3]. Zhu S, Li H, Chen D and Li Y 2018 Multi-Channel Meeting Recognition with Source Separation and Topic Modeling IEEE Signal Processing Lett. 25(5) p 695-698

[4]. Rickard S, Yilmaz O and Herault M 2000 Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures Pro. IEEE Int. Conf. Acoustics Speech Signal Processing 6 p 3466-3469

[5]. Han Y and Wang D 2020 Singing Voice Separation from Music Accompaniment for Monaural Recordings IEEE/ACM Trans. Audio Speech Language Processing 28 p 2178-2193

[6]. Wang Z, Liao W and Liu M 2020 DuET-Net: A dual-branch network for speech separation with an application to noise-robust ASR IEEE/ACM Trans. Audio Speech Language Processing 28 p 2605-2618

[7]. Zhang Y and Nguyen T 2020 Speech recognition using self-supervised learning and wav2vec2 Pro. IEEE Int. Conf. Acoustics Speech Signal Processing p 6904-6908

[8]. Hyvärinen A and Oja E 1999 Fast and robust fixed-point algorithms for independent component analysis IEEE Trans. Neural Networks 10(3) p 626-634 doi:10.1109/72.761722

[9]. Le Roux J, Hershey J R, and Wand M, 2014 Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups IEEE Signal Processing Magazine 31(3) p 82-97

[10]. Kameoka H, Miyoshi M, Saruwatari H and Nakatani T 2005 Blind extraction of audiosources using non-negative matrix factorization with time-frequency masking IEEE Int. Conf. Acoustics Speech Signal Processing p 393-396

Cite this article

Yin,C. (2024). An optimized approach to speech transcription using blind source separation and speech-to-text machine learning models. Applied and Computational Engineering,30,131-138.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 2023 International Conference on Machine Learning and Automation

ISBN：978-1-83558-285-5(Print) / 978-1-83558-286-2(Online)
Editor：Mustafa İSTANBULLU
Conference website: https://2023.confmla.org/
Conference date: 18 October 2023
Series: Applied and Computational Engineering
Volume number: Vol.30
ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. Li Y and Wang D 2021 Noise-Robust Text-Dependent Speaker Verification based on Deep Neural Networks IEEE Access 9 p 1-11

[2]. Chen J and Wang D 2018 Speaker-Independent Speech Recognition System for Multi-Speaker Scenarios using Convolutional Neural Networks IEEE Access 6 p 78317-78324

[3]. Zhu S, Li H, Chen D and Li Y 2018 Multi-Channel Meeting Recognition with Source Separation and Topic Modeling IEEE Signal Processing Lett. 25(5) p 695-698

[4]. Rickard S, Yilmaz O and Herault M 2000 Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures Pro. IEEE Int. Conf. Acoustics Speech Signal Processing 6 p 3466-3469

[5]. Han Y and Wang D 2020 Singing Voice Separation from Music Accompaniment for Monaural Recordings IEEE/ACM Trans. Audio Speech Language Processing 28 p 2178-2193

[6]. Wang Z, Liao W and Liu M 2020 DuET-Net: A dual-branch network for speech separation with an application to noise-robust ASR IEEE/ACM Trans. Audio Speech Language Processing 28 p 2605-2618

[7]. Zhang Y and Nguyen T 2020 Speech recognition using self-supervised learning and wav2vec2 Pro. IEEE Int. Conf. Acoustics Speech Signal Processing p 6904-6908

[8]. Hyvärinen A and Oja E 1999 Fast and robust fixed-point algorithms for independent component analysis IEEE Trans. Neural Networks 10(3) p 626-634 doi:10.1109/72.761722

[9]. Le Roux J, Hershey J R, and Wand M, 2014 Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups IEEE Signal Processing Magazine 31(3) p 82-97

[10]. Kameoka H, Miyoshi M, Saruwatari H and Nakatani T 2005 Blind extraction of audiosources using non-negative matrix factorization with time-frequency masking IEEE Int. Conf. Acoustics Speech Signal Processing p 393-396

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.