The goal of this paper is to study a new approach to text dependent speaker identification using the complex patterns of variation in frequency and amplitude with time while an individual utters a given word through spectrogram segmentation and template matching. The optimally segmented spectrograms are used as a database to successfully identify the unknown individual from his/her voice. The methodology used for identifying, rely on classification of spectrograms (of speech signals), based on dynamic time warping (DTW) matching of conditionally quantized frequency-time domain features of the database samples and the unknown speech sample. Experimental results on a sample collected from 40 speakers show that this methodology can be effectively used to produce a desirable success rate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dynamic Time Warping Based Approach to Text-Dependent Speaker Identification Using Spectrograms


    Contributors:


    Publication date :

    2008-05-01


    Size :

    374428 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Development of an Automatic Speaker-Verification System Using the Dynamic Time-Warping Algorithm

    Geppener, V. V. / Simonchik, K. K. / Haidar, A. S. | British Library Online Contents | 2005


    Learning-Based RF Fingerprinting for Device Identification using Amplitude-Phase Spectrograms

    Mohammad, Abdullahi / Ashraf, Mateen / Valkama, Mikko et al. | IEEE | 2023


    Speech Recognition using Dynamic Time Warping

    Amin, Talal Bin / Mahmood, Iftekhar | IEEE | 2008


    A real-time text-independent speaker identification system

    Cordella, L.P. / Foggia, P. / Sansone, C. et al. | IEEE | 2003


    A Real-Time Text-Independent Speaker Identification System

    Cordella, L. / Foggia, P. / Sansone, C. et al. | British Library Conference Proceedings | 2003