Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling. / Perez Zarazaga, Pablo; Bäckström, Tom; Sigg, Stephan.

European Signal Processing Conference. IEEE, 2019. (European Signal Processing Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Perez Zarazaga, P, Bäckström, T & Sigg, S 2019, Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling. in European Signal Processing Conference. European Signal Processing Conference, IEEE, European Signal Processing Conference, Coruna, Spain, 02/09/2019. https://doi.org/10.23919/EUSIPCO.2019.8903125

APA

Vancouver

Author

Bibtex - Download

@inproceedings{661eb3afa16a44d29f2c2141d75f75e1,
title = "Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling",
abstract = "Voice user interfaces have increased in popularity, as they enable natural interaction with different applications using one’s voice. To improve their usability and audio quality, several devices could interact to provide a unified voice user interface. However, with devices cooperating and sharing voice-related information, user privacy may be at risk. Therefore, access management rules that preserve user privacy are important. State-of-the-art methods for acoustic pairing of devices provide fingerprinting based on the time-frequency representation of the acoustic signal and error-correction. We propose to use such acoustic fingerprinting to authorise devices which are acoustically close. We aim to obtain fingerprints of ambient audio adapted to the requirements of voice user interfaces. Our experiments show that the responsiveness and robustness is improved by combining overlapping windows and decorrelating transforms.",
keywords = "Voice user interface, Acoustic Pairing, Audio Fingerprint, DCT",
author = "{Perez Zarazaga}, Pablo and Tom B{\"a}ckstr{\"o}m and Stephan Sigg",
note = "K{\"a}sikirjoitus avataan, kun julkaisu IEEE:n tietokannassa.",
year = "2019",
doi = "10.23919/EUSIPCO.2019.8903125",
language = "English",
series = "European Signal Processing Conference",
publisher = "IEEE",
booktitle = "European Signal Processing Conference",
address = "United States",

}

RIS - Download

TY - GEN

T1 - Robust and Responsive Acoustic Pairing of Devices Using Decorrelating Time-Frequency Modelling

AU - Perez Zarazaga, Pablo

AU - Bäckström, Tom

AU - Sigg, Stephan

N1 - Käsikirjoitus avataan, kun julkaisu IEEE:n tietokannassa.

PY - 2019

Y1 - 2019

N2 - Voice user interfaces have increased in popularity, as they enable natural interaction with different applications using one’s voice. To improve their usability and audio quality, several devices could interact to provide a unified voice user interface. However, with devices cooperating and sharing voice-related information, user privacy may be at risk. Therefore, access management rules that preserve user privacy are important. State-of-the-art methods for acoustic pairing of devices provide fingerprinting based on the time-frequency representation of the acoustic signal and error-correction. We propose to use such acoustic fingerprinting to authorise devices which are acoustically close. We aim to obtain fingerprints of ambient audio adapted to the requirements of voice user interfaces. Our experiments show that the responsiveness and robustness is improved by combining overlapping windows and decorrelating transforms.

AB - Voice user interfaces have increased in popularity, as they enable natural interaction with different applications using one’s voice. To improve their usability and audio quality, several devices could interact to provide a unified voice user interface. However, with devices cooperating and sharing voice-related information, user privacy may be at risk. Therefore, access management rules that preserve user privacy are important. State-of-the-art methods for acoustic pairing of devices provide fingerprinting based on the time-frequency representation of the acoustic signal and error-correction. We propose to use such acoustic fingerprinting to authorise devices which are acoustically close. We aim to obtain fingerprints of ambient audio adapted to the requirements of voice user interfaces. Our experiments show that the responsiveness and robustness is improved by combining overlapping windows and decorrelating transforms.

KW - Voice user interface

KW - Acoustic Pairing

KW - Audio Fingerprint

KW - DCT

U2 - 10.23919/EUSIPCO.2019.8903125

DO - 10.23919/EUSIPCO.2019.8903125

M3 - Conference contribution

T3 - European Signal Processing Conference

BT - European Signal Processing Conference

PB - IEEE

ER -

ID: 35815509