A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients

Tay Jyi Lin; Chen Zong Liao; You Jia Hu; Wei Cheng Hsu; Zheng Xian Wu; Shao Yu Wang; Chun Ming Huang; Ying Hui Lai; Chingwei Yeh; Jinn Shyan Wang

doi:10.1109/ASP-DAC52403.2022.9712584

A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients

Tay Jyi Lin, Chen Zong Liao, You Jia Hu, Wei Cheng Hsu, Zheng Xian Wu, Shao Yu Wang, Chun Ming Huang, Ying Hui Lai, Chingwei Yeh, Jinn Shyan Wang

Department of Biomedical Engineering

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

3 Scopus citations

Abstract

This paper presents the first dysarthric voice conversion SoC, which can translate stroke patients' voice into more intelligible and clearer speech in real time. The SoC is composed of a RISC-V MPU and a compact DNN engine with a single 16-bit multiply-accumulator, which improves 12x performance and > 100x energy efficiency, and has been implemented in 40nm CMOS. The silicon area is 0.68×0.79mm2, and the measured power is 18.4mW for converting 3-sec dysarthric voice within 0.5 sec (at 200MHz and 0.8V) and 4.8mW for conversion < 1 sec (at 100MHz and 0.6V).

Original language	English
Title of host publication	ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7-8
Number of pages	2
ISBN (Electronic)	9781665421355
DOIs	https://doi.org/10.1109/ASP-DAC52403.2022.9712584
State	Published - 2022
Event	27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022 - Virtual, Online, Taiwan Duration: 17 Jan 2022 → 20 Jan 2022

Publication series

Name	Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Volume	2022-January

Conference

Conference	27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022
Country/Territory	Taiwan
City	Virtual, Online
Period	17/01/22 → 20/01/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ASP-DAC52403.2022.9712584

Cite this

Lin, T. J., Liao, C. Z., Hu, Y. J., Hsu, W. C., Wu, Z. X., Wang, S. Y., Huang, C. M., Lai, Y. H., Yeh, C., & Wang, J. S. (2022). A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients. In ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings (pp. 7-8). (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC; Vol. 2022-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASP-DAC52403.2022.9712584

Lin, Tay Jyi ; Liao, Chen Zong ; Hu, You Jia et al. / A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients. ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 7-8 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC).

@inproceedings{3fe6bbd8ab614cd4a511ee7989f3c7e3,

title = "A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients",

abstract = "This paper presents the first dysarthric voice conversion SoC, which can translate stroke patients' voice into more intelligible and clearer speech in real time. The SoC is composed of a RISC-V MPU and a compact DNN engine with a single 16-bit multiply-accumulator, which improves 12x performance and > 100x energy efficiency, and has been implemented in 40nm CMOS. The silicon area is 0.68×0.79mm2, and the measured power is 18.4mW for converting 3-sec dysarthric voice within 0.5 sec (at 200MHz and 0.8V) and 4.8mW for conversion < 1 sec (at 100MHz and 0.6V).",

author = "Lin, {Tay Jyi} and Liao, {Chen Zong} and Hu, {You Jia} and Hsu, {Wei Cheng} and Wu, {Zheng Xian} and Wang, {Shao Yu} and Huang, {Chun Ming} and Lai, {Ying Hui} and Chingwei Yeh and Wang, {Jinn Shyan}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022 ; Conference date: 17-01-2022 Through 20-01-2022",

year = "2022",

doi = "10.1109/ASP-DAC52403.2022.9712584",

language = "English",

series = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7--8",

booktitle = "ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings",

address = "美國",

}

Lin, TJ, Liao, CZ, Hu, YJ, Hsu, WC, Wu, ZX, Wang, SY, Huang, CM, Lai, YH, Yeh, C & Wang, JS 2022, A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients. in ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings. Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC, vol. 2022-January, Institute of Electrical and Electronics Engineers Inc., pp. 7-8, 27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022, Virtual, Online, Taiwan, 17/01/22. https://doi.org/10.1109/ASP-DAC52403.2022.9712584

A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients. / Lin, Tay Jyi; Liao, Chen Zong; Hu, You Jia et al.
ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 7-8 (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC; Vol. 2022-January).

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

TY - GEN

T1 - A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients

AU - Lin, Tay Jyi

AU - Liao, Chen Zong

AU - Hu, You Jia

AU - Hsu, Wei Cheng

AU - Wu, Zheng Xian

AU - Wang, Shao Yu

AU - Huang, Chun Ming

AU - Lai, Ying Hui

AU - Yeh, Chingwei

AU - Wang, Jinn Shyan

PY - 2022

Y1 - 2022

N2 - This paper presents the first dysarthric voice conversion SoC, which can translate stroke patients' voice into more intelligible and clearer speech in real time. The SoC is composed of a RISC-V MPU and a compact DNN engine with a single 16-bit multiply-accumulator, which improves 12x performance and > 100x energy efficiency, and has been implemented in 40nm CMOS. The silicon area is 0.68×0.79mm2, and the measured power is 18.4mW for converting 3-sec dysarthric voice within 0.5 sec (at 200MHz and 0.8V) and 4.8mW for conversion < 1 sec (at 100MHz and 0.6V).

AB - This paper presents the first dysarthric voice conversion SoC, which can translate stroke patients' voice into more intelligible and clearer speech in real time. The SoC is composed of a RISC-V MPU and a compact DNN engine with a single 16-bit multiply-accumulator, which improves 12x performance and > 100x energy efficiency, and has been implemented in 40nm CMOS. The silicon area is 0.68×0.79mm2, and the measured power is 18.4mW for converting 3-sec dysarthric voice within 0.5 sec (at 200MHz and 0.8V) and 4.8mW for conversion < 1 sec (at 100MHz and 0.6V).

UR - http://www.scopus.com/inward/record.url?scp=85126099742&partnerID=8YFLogxK

U2 - 10.1109/ASP-DAC52403.2022.9712584

DO - 10.1109/ASP-DAC52403.2022.9712584

M3 - Conference contribution

AN - SCOPUS:85126099742

T3 - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

SP - 7

EP - 8

BT - ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th Asia and South Pacific Design Automation Conference, ASP-DAC 2022

Y2 - 17 January 2022 through 20 January 2022

ER -

Lin TJ, Liao CZ, Hu YJ, Hsu WC, Wu ZX, Wang SY et al. A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients. In ASP-DAC 2022 - 27th Asia and South Pacific Design Automation Conference, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 7-8. (Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC). doi: 10.1109/ASP-DAC52403.2022.9712584

A 40nm CMOS SoC for Real-Time Dysarthric Voice Conversion of Stroke Patients

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this