Extract voice information using high-speed camera

Mariko Akutsu, Yasuhiro Oikawa, Yoshio Yamasaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Conversation is one of the most important channels for human beings. To help communications, speech recognition technologies have been developed. Above all, in a conversation, not only contents of utterances but also intonations and tones include important information regarding a speaker's intention. To study the sphere of human speech, microphones are typically used to record voices. However, since microphones have to be set around a space, their existences affect a physical behavior of the sound field. To challenge this problem, we have suggested a recording method using a high-speed camera. By using a high-speed camera for recording sound vibrations, it can record two or more points within the range of the camera at the same time and can record from a distance, without interfering with the sound fields. In this study, we extract voice information using high-speed videos which capture both a face and a cervical part of the subject. This method allows recording skin vibrations which contain voices with individuality and extrapolating sound waves by using an image processing method. The result of the experiment shows that a high-speed camera is capable of recording voice information.

Original languageEnglish
Title of host publicationProceedings of Meetings on Acoustics
Volume19
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event21st International Congress on Acoustics, ICA 2013 - 165th Meeting of the Acoustical Society of America - Montreal, QC, Canada
Duration: 2013 Jun 22013 Jun 7

Other

Other21st International Congress on Acoustics, ICA 2013 - 165th Meeting of the Acoustical Society of America
CountryCanada
CityMontreal, QC
Period13/6/213/6/7

Fingerprint

high speed cameras
recording
conversation
sound fields
microphones
vibration
speech recognition
sound waves
image processing
communication
cameras
high speed
acoustics

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

Akutsu, M., Oikawa, Y., & Yamasaki, Y. (2013). Extract voice information using high-speed camera. In Proceedings of Meetings on Acoustics (Vol. 19). [055019] https://doi.org/10.1121/1.4800866

Extract voice information using high-speed camera. / Akutsu, Mariko; Oikawa, Yasuhiro; Yamasaki, Yoshio.

Proceedings of Meetings on Acoustics. Vol. 19 2013. 055019.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Akutsu, M, Oikawa, Y & Yamasaki, Y 2013, Extract voice information using high-speed camera. in Proceedings of Meetings on Acoustics. vol. 19, 055019, 21st International Congress on Acoustics, ICA 2013 - 165th Meeting of the Acoustical Society of America, Montreal, QC, Canada, 13/6/2. https://doi.org/10.1121/1.4800866
Akutsu M, Oikawa Y, Yamasaki Y. Extract voice information using high-speed camera. In Proceedings of Meetings on Acoustics. Vol. 19. 2013. 055019 https://doi.org/10.1121/1.4800866
Akutsu, Mariko ; Oikawa, Yasuhiro ; Yamasaki, Yoshio. / Extract voice information using high-speed camera. Proceedings of Meetings on Acoustics. Vol. 19 2013.
@inproceedings{4c415c9c0473430c9c6b42e1a7769d4b,
title = "Extract voice information using high-speed camera",
abstract = "Conversation is one of the most important channels for human beings. To help communications, speech recognition technologies have been developed. Above all, in a conversation, not only contents of utterances but also intonations and tones include important information regarding a speaker's intention. To study the sphere of human speech, microphones are typically used to record voices. However, since microphones have to be set around a space, their existences affect a physical behavior of the sound field. To challenge this problem, we have suggested a recording method using a high-speed camera. By using a high-speed camera for recording sound vibrations, it can record two or more points within the range of the camera at the same time and can record from a distance, without interfering with the sound fields. In this study, we extract voice information using high-speed videos which capture both a face and a cervical part of the subject. This method allows recording skin vibrations which contain voices with individuality and extrapolating sound waves by using an image processing method. The result of the experiment shows that a high-speed camera is capable of recording voice information.",
author = "Mariko Akutsu and Yasuhiro Oikawa and Yoshio Yamasaki",
year = "2013",
doi = "10.1121/1.4800866",
language = "English",
volume = "19",
booktitle = "Proceedings of Meetings on Acoustics",

}

TY - GEN

T1 - Extract voice information using high-speed camera

AU - Akutsu, Mariko

AU - Oikawa, Yasuhiro

AU - Yamasaki, Yoshio

PY - 2013

Y1 - 2013

N2 - Conversation is one of the most important channels for human beings. To help communications, speech recognition technologies have been developed. Above all, in a conversation, not only contents of utterances but also intonations and tones include important information regarding a speaker's intention. To study the sphere of human speech, microphones are typically used to record voices. However, since microphones have to be set around a space, their existences affect a physical behavior of the sound field. To challenge this problem, we have suggested a recording method using a high-speed camera. By using a high-speed camera for recording sound vibrations, it can record two or more points within the range of the camera at the same time and can record from a distance, without interfering with the sound fields. In this study, we extract voice information using high-speed videos which capture both a face and a cervical part of the subject. This method allows recording skin vibrations which contain voices with individuality and extrapolating sound waves by using an image processing method. The result of the experiment shows that a high-speed camera is capable of recording voice information.

AB - Conversation is one of the most important channels for human beings. To help communications, speech recognition technologies have been developed. Above all, in a conversation, not only contents of utterances but also intonations and tones include important information regarding a speaker's intention. To study the sphere of human speech, microphones are typically used to record voices. However, since microphones have to be set around a space, their existences affect a physical behavior of the sound field. To challenge this problem, we have suggested a recording method using a high-speed camera. By using a high-speed camera for recording sound vibrations, it can record two or more points within the range of the camera at the same time and can record from a distance, without interfering with the sound fields. In this study, we extract voice information using high-speed videos which capture both a face and a cervical part of the subject. This method allows recording skin vibrations which contain voices with individuality and extrapolating sound waves by using an image processing method. The result of the experiment shows that a high-speed camera is capable of recording voice information.

UR - http://www.scopus.com/inward/record.url?scp=84878964371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878964371&partnerID=8YFLogxK

U2 - 10.1121/1.4800866

DO - 10.1121/1.4800866

M3 - Conference contribution

AN - SCOPUS:84878964371

VL - 19

BT - Proceedings of Meetings on Acoustics

ER -