Browsing by Subject "Speech recognition systems."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Computationally efficient voice dialing system
    (1998) Solmaz, Mustafa Hakan
    Subband based feature parameters are becoming widely used for speech recognition purposes. In this thesis a subband-based, small-vocabulary, speaker-dependent, isolated-word recognition system is proposed. The most distinctive property of the proposed system is its low computational cost which enables it to run at real-time on a simple microcontroller. The system is used as the core of a voice dialer which is designed to work together with Karel switchboxes. In training section first, an energy-based endpoint (startingpoint) detection method is applied for speech detection. Then feature extraction is applied on a fixed length, pcm-quantized (a-law) speech long enough to cover a single word. In recognition section template matching is used to find the most likely vocabulary element. A recognition rate of 93% is obtained in the simulations.
  • Thumbnail Image
    ItemOpen Access
    New methods for robust speech recognition
    (1995) Erzin, Engin
    New methods of feature extraction, end-point detection and speech enhcincement are developed for a robust speech recognition system. The methods of feature extraction and end-point detection are based on wavelet analysis or subband analysis of the speech signal. Two new sets of speech feature parameters, SUBLSF’s and SUBCEP’s, are introduced. Both parameter sets are based on subband analysis. The SUBLSF feature parameters are obtained via linear predictive analysis on subbands. These speech feature parameters can produce better results than the full-band parameters when the noise is colored. The SUBCEP parameters are based on wavelet analysis or equivalently the multirate subband analysis of the speech signal. The SUBCEP parameters also provide robust recognition performance by appropriately deemphasizing the frequency bands corrupted by noise. It is experimentally observed that the subband analysis based feature parameters are more robust than the commonly used full-band analysis based parameters in the presence of car noise. The a-stable random processes can be used to model the impulsive nature of the public network telecommunication noise. Adaptive filtering are developed for Q-stable random processes. Adaptive noise cancelation techniques are used to reduce the mismacth between training and testing conditions of the recognition system over telephone lines. Another important problem in isolated speech recognition is to determine the boundaries of the speech utterances or words. Precise boundary detection of utterances improves the performance of speech recognition systems. A new distance measure based on the subband energy levels is introduced for endpoint detection.