APHONIC: Adaptive thresholding for noise cancellation in smart mobile environments

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

Abstract

We propose a signal-channel, adaptive threshold selection technique for binary mask construction, namely APHONIC, (AdaPtive tHreshOlding for NoIse Cancellation) for smart mobile environments. Using this mask, we introduce two noise cancellation techniques that perform robustly in the presence of real-world interfering signals that are typically encountered by mobile users: a violin busker, a subway and busy city square sounds. We demonstrate that when the power of the time-frequency components of the voice of a mobile user does not significantly overlap with the components of the interference signal, the threshold learning and noise cancellation techniques significantly improve the Signal-to-Interference Ratio (SIR) and the Signal-Distortion Ratio (SDR) of the recovered voice. When a mobile user's speech is mixed with music or with the sounds of a city square, or subway station, the speech energy is captured by a few large magnitude coefficients and APHONIC improves the SIR by greater than 20dB and the SDR by up to 5dB. The robustness of the threshold selection step and the noise cancellation algorithms is evaluated using environments typically experienced by mobile phone users. Listening tests indicate that the interference signal is no longer audible in the denoised signals. We outline how this approach could be used in many mobile voice-driven applications.

Original languageEnglish
Title of host publication2017 IEEE 13th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017
PublisherIEEE Computer Society
Pages285-292
Number of pages8
ISBN (Electronic)9781538638392
DOIs
Publication statusPublished - 20 Nov 2017
Event13th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017 - Rome, Italy
Duration: 9 Oct 201711 Oct 2017

Publication series

NameInternational Conference on Wireless and Mobile Computing, Networking and Communications
Volume2017-October
ISSN (Print)2161-9646
ISSN (Electronic)2161-9654

Conference

Conference13th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2017
Country/TerritoryItaly
CityRome
Period9/10/1711/10/17

Keywords

  • Blind Source Separation
  • Human Computer Interaction
  • Mobile Computing
  • Mobile Voice-driven Applications
  • Noise Cancellation

Fingerprint

Dive into the research topics of 'APHONIC: Adaptive thresholding for noise cancellation in smart mobile environments'. Together they form a unique fingerprint.

Cite this