The objective of this thesis is to build a phrase recognition system under noisy environment that can be used in real-life. In this system, the noisy speech is first filtered by the enhanced spectral subtraction method to reduce the noise level. Then the MFCC with cepstral mean subtraction is applied to extract the speech features. Finally, hidden Markov model (HMM) is used in the last stage to build the probabilistic model for each phrase. A Mandarin microphone database of 514 company names that are in Taiwan¡¦s stock market is collected. A speaker independent noisy phrase recognition system is then implemented. This system has been tested under various noise environments and different noise strengths.

This thesis attempts to address the problem of how best to remedy different types of channel distortions on speech when that speech is to be used in automatic speaker recognition and verification systems. Automatic speaker recognition is when a person's voice is analysed by a machine and the person's identity is worked out by the comparison of speech features to a known set of speech features. Automatic speaker verification is when a person claims an identity and the machine determines if that claimed identity is correct or whether that person is an impostor. Channel distortion occurs whenever information is sent electronically through any type of channel whether that channel is a basic wired telephone channel or a wireless channel. The types of distortion that can corrupt the information include time-variant or time-invariant filtering of the information or the addition of 'thermal noise' to the information, both of these types of distortion can cause varying degrees of error in information being received and analysed. The experiments presented in this thesis investigate the effects of channel distortion on the average speaker recognition rates and testing the effectiveness of various channel compensation algorithms designed to mitigate the effects of channel distortion. The speaker recognition system was represented by a basic recognition algorithm consisting of: speech analysis, extraction of feature vectors in the form of the Mel-Cepstral Coefficients, and a classification part based on the minimum distance rule. Two types of channel distortion were investigated: • Convolutional (or lowpass filtering) effects • Addition of white Gaussian noise Three different methods of channel compensation were tested: • Cepstral Mean Subtraction (CMS) • RelAtive SpecTrAl (RASTA) Processing • Constant Modulus Algorithm (CMA) The results from the experiments showed that for both CMS and RASTA processing that filtering at low cutoff frequencies, (3 or 4 kHz), produced improvements in the average speaker recognition rates compared to speech with no compensation. The levels of improvement due to RASTA processing were higher than the levels achieved due to the CMS method. Neither the CMS or RASTA methods were able to improve accuracy of the speaker recognition system for cutoff frequencies of 5 kHz, 6 kHz or 7 kHz. In the case of noisy speech all methods analysed were able to compensate for high SNR of 40 dB and 30 dB and only RASTA processing was able to compensate and improve the average recognition rate for speech corrupted with a high level of noise (SNR of 20 dB and 10 dB).