About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
ct 15(4): e3

Research Article

Assessing the efficacy of benchmarks for automatic speech accent recognition

Download1634 downloads
Cite
BibTeX Plain Text
  • @ARTICLE{10.4108/icst.mobimedia.2015.259033,
        author={Benjamin Bock and Lior Shamir},
        title={Assessing the efficacy of benchmarks for automatic speech accent recognition},
        journal={EAI Endorsed Transactions on Creative Technologies},
        volume={2},
        number={4},
        publisher={ACM},
        journal_a={CT},
        year={2015},
        month={8},
        keywords={speech, accent, audio analysis},
        doi={10.4108/icst.mobimedia.2015.259033}
    }
    
  • Benjamin Bock
    Lior Shamir
    Year: 2015
    Assessing the efficacy of benchmarks for automatic speech accent recognition
    CT
    EAI
    DOI: 10.4108/icst.mobimedia.2015.259033
Benjamin Bock1, Lior Shamir1,*
  • 1: Lawrence Technological University
*Contact email: lshamir@mtu.edu

Abstract

Speech accents can possess valuable information about the speaker, and can be used in intelligent multimedia-based human-computer interfaces. The performance of algorithms for automatic classification of accents is often evaluated using audio datasets that include recording samples of different people, representing different accents. Here we describe a method that can detect bias in accent datasets, and apply the method to two accent identification datasets to reveal the existence of dataset bias, meaning that the datasets can be classified with accuracy higher than random even if the tested algorithm has no ability to analyze speech accent. We used the datasets by separating one second of silence from the beginning of each audio sample, such that the one-second sample did not contain voice, and therefore no information about the accent. An audio classification method was then applied to the datasets of silent audio samples, and provided classification accuracy significantly higher than random. These results indicate that the performance of accent classification algorithms measured using some accent classification benchmarks can be biased, and can be driven by differences in the background noise rather than the auditory features of the accents.

Keywords
speech, accent, audio analysis
Published
2015-08-03
Publisher
ACM
http://dx.doi.org/10.4108/icst.mobimedia.2015.259033

Copyright © 2015 B. Bock et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/3.0/), which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited.

EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL