Scribd Logo
Upload

Welcome to Scribd!

  • 83 views

    MFCC CZT

    Uploaded by

    Sufyan Nikanin
    This document summarizes a seminar on comparing acoustic features of MFCC and CZT-based cepstrum for speech recognition. MFCC is commonly used in speech recognition but the seminar evaluated combining it with CZT-based features. An experiment tested recognition rates using MFCC alone and combined with CZT on different datasets, finding the combined approach achieved higher accuracy. In conclusion, the combination of MFCC and CZT-based features enhanced frequency resolution of transient speech signals, improving recognition accuracy over MFCC alone.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd

    MFCC CZT

    Uploaded by

    Sufyan Nikanin
    83 views10 pages
    This document summarizes a seminar on comparing acoustic features of MFCC and CZT-based cepstrum for speech recognition. MFCC is commonly used in speech recognition but the seminar evaluated combining it with CZT-based features. An experiment tested recognition rates using MFCC alone and combined with CZT on different datasets, finding the combined approach achieved higher accuracy. In conclusion, the combination of MFCC and CZT-based features enhanced frequency resolution of transient speech signals, improving recognition accuracy over MFCC alone.

    Original Description:

    MFCC CZT

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes a seminar on comparing acoustic features of MFCC and CZT-based cepstrum for speech recognition. MFCC is commonly used in speech recognition but the seminar evaluated combining it with CZT-based features. An experiment tested recognition rates using MFCC alone and combined with CZT on different datasets, finding the combined approach achieved higher accuracy. In conclusion, the combination of MFCC and CZT-based features enhanced frequency resolution of transient speech signals, improving recognition accuracy over MFCC alone.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    83 views10 pages

    MFCC CZT

    Uploaded by

    Sufyan Nikanin
    This document summarizes a seminar on comparing acoustic features of MFCC and CZT-based cepstrum for speech recognition. MFCC is commonly used in speech recognition but the seminar evaluated combining it with CZT-based features. An experiment tested recognition rates using MFCC alone and combined with CZT on different datasets, finding the combined approach achieved higher accuracy. In conclusion, the combination of MFCC and CZT-based features enhanced frequency resolution of transient speech signals, improving recognition accuracy over MFCC alone.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 10

    SEMINAR ON

    Acoustic Feature Comparison of MFCC and CZT-based Cepstrum for Speech Recognition

    Guided by:Prof. R.V.Pawar

    Presented by:Neehal B. Jiwane

    Introduction
    The Mel-Frequency Cepstral Coefficients (MFCC) are the most widely used features in speech recognition field. Automatic speech recognition (ASR) systems. Feature extraction. The MFCC parameters perform better than others in the recognition accuracy.

    MFCC

    Fig. 1. MFCC Block Diagram

    Chirp Z-Transform

    Fig 2: Oreration in CZT

    Data Time Warping


    DTW algorithm is based on Dynamic Programming techniques

    Fig. 3. A Warping between two time series

    Experiment condition
    Process 1) Speaker 2) Tools 3) Environment 4) Sampling Frequency, fs 4) Utterance Description 3 Female 3 Male Cool Edit Pro 2.0 tool Laboratory 300-3000 Hz Noisy area

    RECOGNITION
    Testing Set Testing Number Correct Number Percentage % Testing Set Testing Number Correct Number Percentage %

    0 1 2 3 4 5 6 7 8 9

    8 8 8 8 8 8 8 8 8 8

    6 7 8 3 4 8 6 8 8 8

    75 87.5 100 37.5 50 100 75 100 100 100

    0 1 2 3 4 5 6 7 8 9

    8 8 8 8 8 8 8 8 8 8

    6 7 8 4 5 8 7 8 8 8

    75 87.5 100 50 62.5 100 87.5 100 100 100

    conditions:fl=300,fh=3000,M=256 Table 1. Recognition Rate of the MFCC Table 2. Recognition Rate of the MFCC+CZTBased

    Testing Set

    Testing Number

    Correct Number

    Percenta ge % 75 87.5 100 50 62.5 100 87.5 100 100 100 fl=300,fh=3000,M=256 Table 4. Different Cepstral Coefficients Testing Number Correct Number Percentage / % 80 66 79.825 80 69 86.25 Cepstral Coefficients MFCC MFCC&CZTbased

    0 1 2 3 4 5 6 7 8 9

    8 8 8 8 8 8 8 8 8 8

    6 7 8 6 6 8 7 8 8 8

    conditions:fl=300,fh=3000,M=512 Table 3. Recognition Rate of the MFCC+CZTBased

    Conclusion
    The design and implementation of the experiment, we come to the following conclusions, a new approach, called CZT-based algorithm, was developed to extract speech signals that are highly transient in nature. We combine the CZTbased method with MFCC has demonstrated its superiority over the previously reported MFCC method in that the frequency resolution of the highly transient speech signals is much enhanced, with better accuracy, widespread integration of speech recognition technology into enduser applications is ahead.

    REFERENCES
    [1] L.R. Rabiner, B.Gold, in: Theory and Application of Digital Signal Processing, Prentice-Hail, Englewood Cliffs, NJ, 1975, p.393. [2] J.P. Openshaw, Z.P. Sun, J.S. Mason, "A comparison of composite features under degraded speech in speaker recognition", Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. [3] R. Vergin, D. OShaughnessy, V. Gupta, "Compensated mel frequency cepstrum coefficients", Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. [4] Picone J W, "Signal modeling techniques in speech recognition", In Proceedings of the IEEE,1993,81(9):1215- 1247.

    [5] Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques. Lindasalwa Muda, Mumtaj Begam and I. Elamvazuthi

    You might also like