Speech Stuttering Detection and Removal Using Deep Neural Networks

Shaswat Rajput; Ruban Nersisson; Alex Noel Joseph Raj; A. Mary Mekala; Olga Frolova; Elena Lyakso

doi:10.1007/978-981-16-6554-7_50

Speech Stuttering Detection and Removal Using Deep Neural Networks

Shaswat Rajput, Ruban Nersisson, Alex Noel Joseph Raj, A. Mary Mekala, Olga Frolova, Elena Lyakso

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Abstract

There are more than 70 million people worldwide who suffer from stuttering problems. This will affect the confidence of public speaking in people who suffer from this issue. To solve this problem many people take therapy sessions but the therapy sessions are a temporary solution, as soon as they leave therapy sessions this problem might arise again. This work aims to use state of the art machine learning algorithms that have improved over the past few years to solve this problem. We have used the dataset from UCLASS archives which provide the data for stuttered speech in.wav format with time-aligned transcriptions. We have tried different algorithms and optimized our model by hyper parameter tuning to maximize the model’s accuracy. The algorithm is tested on random speech data with low to heavy stuttering from the same dataset, and it is observed that there is significant reduction in the Word Error Rate (WER) for most of the test cases.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Computer Engineering and Networks
Editors	Qi Liu, Xiaodong Liu, Bo Chen, Yiming Zhang, Jiansheng Peng
Publisher	Springer Nature
Pages	443-451
Number of pages	9
ISBN (Print)	9789811665530
DOIs	https://doi.org/10.1007/978-981-16-6554-7_50
State	Published - 2022
Event	11th International Conference on Computer Engineering and Networks, CENet2021 - Hechi, China Duration: 21 Oct 2021 → 25 Oct 2021

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	808 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	11th International Conference on Computer Engineering and Networks, CENet2021
Country/Territory	China
City	Hechi
Period	21/10/21 → 25/10/21

Scopus subject areas

Industrial and Manufacturing Engineering

Keywords

Classification
Deep learning
Filtering
Speech stuttering
Word Error Rate

Access to Document

10.1007/978-981-16-6554-7_50

Cite this

Rajput, S., Nersisson, R., Raj, A. N. J., Mary Mekala, A., Frolova, O., & Lyakso, E. (2022). Speech Stuttering Detection and Removal Using Deep Neural Networks. In Q. Liu, X. Liu, B. Chen, Y. Zhang, & J. Peng (Eds.), Proceedings of the 11th International Conference on Computer Engineering and Networks (pp. 443-451). (Lecture Notes in Electrical Engineering; Vol. 808 LNEE). Springer Nature. https://doi.org/10.1007/978-981-16-6554-7_50

Rajput, Shaswat ; Nersisson, Ruban ; Raj, Alex Noel Joseph ; Mary Mekala, A. ; Frolova, Olga ; Lyakso, Elena. / Speech Stuttering Detection and Removal Using Deep Neural Networks. Proceedings of the 11th International Conference on Computer Engineering and Networks. editor / Qi Liu ; Xiaodong Liu ; Bo Chen ; Yiming Zhang ; Jiansheng Peng. Springer Nature, 2022. pp. 443-451 (Lecture Notes in Electrical Engineering).

@inproceedings{37cb3771bb6f4af68a5ca08db3405427,

title = "Speech Stuttering Detection and Removal Using Deep Neural Networks",

abstract = "There are more than 70 million people worldwide who suffer from stuttering problems. This will affect the confidence of public speaking in people who suffer from this issue. To solve this problem many people take therapy sessions but the therapy sessions are a temporary solution, as soon as they leave therapy sessions this problem might arise again. This work aims to use state of the art machine learning algorithms that have improved over the past few years to solve this problem. We have used the dataset from UCLASS archives which provide the data for stuttered speech in.wav format with time-aligned transcriptions. We have tried different algorithms and optimized our model by hyper parameter tuning to maximize the model{\textquoteright}s accuracy. The algorithm is tested on random speech data with low to heavy stuttering from the same dataset, and it is observed that there is significant reduction in the Word Error Rate (WER) for most of the test cases.",

keywords = "Classification, Deep learning, Filtering, Speech stuttering, Word Error Rate",

author = "Shaswat Rajput and Ruban Nersisson and Raj, {Alex Noel Joseph} and {Mary Mekala}, A. and Olga Frolova and Elena Lyakso",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 11th International Conference on Computer Engineering and Networks, CENet2021 ; Conference date: 21-10-2021 Through 25-10-2021",

year = "2022",

doi = "10.1007/978-981-16-6554-7_50",

language = "English",

isbn = "9789811665530",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Nature",

pages = "443--451",

editor = "Qi Liu and Xiaodong Liu and Bo Chen and Yiming Zhang and Jiansheng Peng",

booktitle = "Proceedings of the 11th International Conference on Computer Engineering and Networks",

address = "Germany",

}

Rajput, S, Nersisson, R, Raj, ANJ, Mary Mekala, A, Frolova, O & Lyakso, E 2022, Speech Stuttering Detection and Removal Using Deep Neural Networks. in Q Liu, X Liu, B Chen, Y Zhang & J Peng (eds), Proceedings of the 11th International Conference on Computer Engineering and Networks. Lecture Notes in Electrical Engineering, vol. 808 LNEE, Springer Nature, pp. 443-451, 11th International Conference on Computer Engineering and Networks, CENet2021, Hechi, China, 21/10/21. https://doi.org/10.1007/978-981-16-6554-7_50

Speech Stuttering Detection and Removal Using Deep Neural Networks. / Rajput, Shaswat; Nersisson, Ruban; Raj, Alex Noel Joseph; Mary Mekala, A.; Frolova, Olga ; Lyakso, Elena.

Proceedings of the 11th International Conference on Computer Engineering and Networks. ed. / Qi Liu; Xiaodong Liu; Bo Chen; Yiming Zhang; Jiansheng Peng. Springer Nature, 2022. p. 443-451 (Lecture Notes in Electrical Engineering; Vol. 808 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

TY - GEN

T1 - Speech Stuttering Detection and Removal Using Deep Neural Networks

AU - Rajput, Shaswat

AU - Nersisson, Ruban

AU - Raj, Alex Noel Joseph

AU - Mary Mekala, A.

AU - Frolova, Olga

AU - Lyakso, Elena

PY - 2022

Y1 - 2022

N2 - There are more than 70 million people worldwide who suffer from stuttering problems. This will affect the confidence of public speaking in people who suffer from this issue. To solve this problem many people take therapy sessions but the therapy sessions are a temporary solution, as soon as they leave therapy sessions this problem might arise again. This work aims to use state of the art machine learning algorithms that have improved over the past few years to solve this problem. We have used the dataset from UCLASS archives which provide the data for stuttered speech in.wav format with time-aligned transcriptions. We have tried different algorithms and optimized our model by hyper parameter tuning to maximize the model’s accuracy. The algorithm is tested on random speech data with low to heavy stuttering from the same dataset, and it is observed that there is significant reduction in the Word Error Rate (WER) for most of the test cases.

AB - There are more than 70 million people worldwide who suffer from stuttering problems. This will affect the confidence of public speaking in people who suffer from this issue. To solve this problem many people take therapy sessions but the therapy sessions are a temporary solution, as soon as they leave therapy sessions this problem might arise again. This work aims to use state of the art machine learning algorithms that have improved over the past few years to solve this problem. We have used the dataset from UCLASS archives which provide the data for stuttered speech in.wav format with time-aligned transcriptions. We have tried different algorithms and optimized our model by hyper parameter tuning to maximize the model’s accuracy. The algorithm is tested on random speech data with low to heavy stuttering from the same dataset, and it is observed that there is significant reduction in the Word Error Rate (WER) for most of the test cases.

KW - Classification

KW - Deep learning

KW - Filtering

KW - Speech stuttering

KW - Word Error Rate

UR - http://www.scopus.com/inward/record.url?scp=85120086451&partnerID=8YFLogxK

U2 - 10.1007/978-981-16-6554-7_50

DO - 10.1007/978-981-16-6554-7_50

M3 - Conference contribution

AN - SCOPUS:85120086451

SN - 9789811665530

T3 - Lecture Notes in Electrical Engineering

SP - 443

EP - 451

BT - Proceedings of the 11th International Conference on Computer Engineering and Networks

A2 - Liu, Qi

A2 - Liu, Xiaodong

A2 - Chen, Bo

A2 - Zhang, Yiming

A2 - Peng, Jiansheng

PB - Springer Nature

T2 - 11th International Conference on Computer Engineering and Networks, CENet2021

Y2 - 21 October 2021 through 25 October 2021

ER -

Rajput S, Nersisson R, Raj ANJ, Mary Mekala A, Frolova O , Lyakso E. Speech Stuttering Detection and Removal Using Deep Neural Networks. In Liu Q, Liu X, Chen B, Zhang Y, Peng J, editors, Proceedings of the 11th International Conference on Computer Engineering and Networks. Springer Nature. 2022. p. 443-451. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-16-6554-7_50

Speech Stuttering Detection and Removal Using Deep Neural Networks

Abstract

Publication series

Conference

Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this