33
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Speaker-independent auditory attention decoding without access to clean speech sources

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Our system separates simultaneous voices and compares them with brain waves of a listener to amplify attended speech.

          Abstract

          Speech perception in crowded environments is challenging for hearing-impaired listeners. Assistive hearing devices cannot lower interfering speakers without knowing which speaker the listener is focusing on. One possible solution is auditory attention decoding in which the brainwaves of listeners are compared with sound sources to determine the attended source, which can then be amplified to facilitate hearing. In realistic situations, however, only mixed audio is available. We utilize a novel speech separation algorithm to automatically separate speakers in mixed audio, with no need for the speakers to have prior training. Our results show that auditory attention decoding with automatically separated speakers is as accurate and fast as using clean speech sounds. The proposed method significantly improves the subjective and objective quality of the attended speaker. Our study addresses a major obstacle in actualization of auditory attention decoding that can assist hearing-impaired listeners and reduce listening effort for normal-hearing subjects.

          Related collections

          Most cited references34

          • Record: found
          • Abstract: not found
          • Article: not found

          Beamforming: a versatile approach to spatial filtering

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            The expectation-maximization algorithm

            T.K. Moon (1996)
              Bookmark
              • Record: found
              • Abstract: not found
              • Book Chapter: not found

              Principal Component Analysis

                Bookmark

                Author and article information

                Journal
                Sci Adv
                Sci Adv
                SciAdv
                advances
                Science Advances
                American Association for the Advancement of Science
                2375-2548
                May 2019
                15 May 2019
                : 5
                : 5
                : eaav6134
                Affiliations
                [1 ]Department of Electrical Engineering, Columbia University, New York, NY, USA.
                [2 ]Zuckerman Mind Brain Behavior Institute, Columbia University, New York, NY, USA.
                [3 ]Department of Neurosurgery, Hofstra-Northwell School of Medicine and Feinstein Institute for Medical Research, Manhasset, New York, NY, USA.
                Author notes
                [*]

                These authors contributed equally to this work.

                []Corresponding author. Email: nima@ 123456ee.columbia.edu
                Author information
                http://orcid.org/0000-0003-2121-000X
                http://orcid.org/0000-0002-3501-9647
                http://orcid.org/0000-0002-7447-3885
                http://orcid.org/0000-0001-7293-1101
                Article
                aav6134
                10.1126/sciadv.aav6134
                6520028
                31106271
                84e79a79-4ea4-41c5-88dc-30cdffc0c396
                Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).

                This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license, which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited.

                History
                : 06 October 2018
                : 09 April 2019
                Funding
                Funded by: doi http://dx.doi.org/10.13039/100000052, NIH Office of the Director;
                Funded by: doi http://dx.doi.org/10.13039/100000179, NSF Office of the Director;
                Categories
                Research Article
                Research Articles
                SciAdv r-articles
                Applied Sciences and Engineering
                Neuroscience
                Neuroscience
                Custom metadata
                Eunice Diego

                Comments

                Comment on this article