In this paper, six noise reduction algorithms had been compared with the use of a set of indicators. Among them are popular noise reduction algorithms such as spectral subtraction, Wiener filtering, MMSE and logMMSE, and two less well-known Wiener-TSNR and Wiener-HRNR algorithms. It is shown that when the noise reduction system is used as preprocessor of automatic speech recognition (ASR) system, only a small amount of speech quality indicators is in satisfactory agreement with the recognition accuracy. In particular, these include Log-Likelihood Ratio (LLR) and Signal Composite Index (SCI) indicators. In addition, it is shown that there is no single algorithm among the considered noise reduction algorithms, which is the best in terms of maximum recognition accuracy for a wide range of input signal-to-noise ratio from minus 10 dB to plus 30 dB.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Performance measures of noise reduction algorithms in voice control channels of UAVs


    Contributors:


    Publication date :

    2015-10-01


    Size :

    481869 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    NOISE-REDUCTION SYSTEM FOR UAVS

    WHITTAKER RICHARD JONATHAN / SIGOUIN TARIQ | European Patent Office | 2018

    Free access

    Noise-reduction system for UAVs

    WHITTAKER RICHARD JONATHAN / SIGOUIN TARIQ | European Patent Office | 2019

    Free access

    Noise Measurements of Tactical UAVs

    Massey, Kevin / Gaeta, Richard | AIAA | 2010


    Detection, recognition and counter measures against unwanted UAVS

    Tchouchenkov, Igor / Segor, Florian / Kollmann, Matthias et al. | Fraunhofer Publica | 2015

    Free access

    Road Noise Identification and Reduction Measures

    Mansinh, Kumbhar S. / Rao, Manchi Venkateswara / R., Prasath et al. | SAE Technical Papers | 2013