Noisy audio feature enhancement using audio-visual speech data

Roland Goecke, Gerasimos Potamianos, Chalapathy Neti

    Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

    30 Citations (Scopus)
    43 Downloads (Pure)

    Abstract

    We investigate improving automatic speech recognition (ASR) in noisy conditions by enhancing noisy audio features using visual speech captured from the speaker's face. The enhancement is achieved by applying a linear filter to the concatenated vector of noisy audio and visual features, obtained by mean square error estimation of the clean audio features in a training stage. The performance of the enhanced audio features is evaluated on two ASR tasks: A connected digits task and speaker-independent, large-vocabulary, continuous speech recognition. In both cases and at sufficiently low signal-to-noise ratios (SNRs), ASR trained on the enhanced audio features significantly outperforms ASR trained on the noisy audio, achieving for example a 46% relative reduction in word error rate on the digits task at -3.5 dB SNR. However, the method fails to capture the full visual modality benefit to ASR, as demonstrated by its comparison to discriminant audio-visual feature fusion introduced in previous work.
    Original languageEnglish
    Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
    PublisherIEEE
    Pages2025-2028
    Number of pages4
    Volume2
    ISBN (Print)0-7803-7402-9
    DOIs
    Publication statusPublished - 2002
    Event2002 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2002 - Salt Lake City, United States
    Duration: 12 May 200217 May 2002

    Publication series

    NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
    Volume2

    Conference

    Conference2002 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2002
    Abbreviated titleICASSP 2012
    Country/TerritoryUnited States
    CitySalt Lake City
    Period12/05/0217/05/02

    Fingerprint

    Dive into the research topics of 'Noisy audio feature enhancement using audio-visual speech data'. Together they form a unique fingerprint.

    Cite this