Many speech segmentation techniques have been proposed to automate phonetic alignment. Most of the techniques require, however, labeled data to train, and perform well only for read, high-quality speech. Automatic phonetic alignment, for lower quality varied data with no labeled training data, the subject of this paper, is a much more challenging domain. An HMMbased automatic speech recognizer was used in this study to determine phonetic sequences and boundaries of “open source” speech data, retrieved from public websites. The HMM models were initially trained using the TIMIT database and subsequently adapted to each passage. Standard frontend features such as MFCC, LPCC and PLP, and features computed by applying the DCT directly to the short-time spectrum (DCTC) were evaluated using TIMIT data. The “best” parameter set was found to be DCTC_78 and these parameters were used to align the speech data of interest.

We propose a way of synthesizing Thai vowels, monophthong and diphthong which consist of nine short-long vowel pairs and three short-long vowel pairs respectively. By adjusting the fundamental frequency or pitch contour, the five tonal of these vowels can be synthesized, leading to a total of 120 phonemes. We evaluate the synthesized monophthongs by comparing the first and second formants to standard in terms of different percentages, which result in 9.89% and 7.44% respectively. For the synthesis of diphthongs, we slide from one vocal-tract vowel to another using linear, logarithmic, or exponential functions.

This paper presents a study of tone classification for continuous Thai speech recognition. A modified autocorrelation algorithm was implemented with pitch detection, and the tone classifier utilized 3-layer feed-forward neural network with back-propagation. The best performance configuration of tone features was obtained with semi-tone scaling and mean-normalization producing a classification accuracy of 72.21%. Also, after considering the effects of final consonants, the average performance of the tone classifier improved to 77.13%. Experimental results showed that the pitch value of a tone with no final consonants has more variation than one with final consonants. Also the classification for tones with voiced final consonant gave better performance than tones with unvoiced final consonants.

This paper describes speech signal modeling techniques which are well-suited to high performance and robust isolated word recognition. We present new techniques for incorporating spectral/temporal information as a function of the temporal position within each word. In particular, spectral/temporal parameters are computed using both variable length blocks with a variable spacing between blocks. We tested features computed with these methods using an alphabet recognition task based on the ISOLET database. The hidden Markov model toolkit (HTK) was used to implement the isolated word recognizer with whole word HMM models. The best accuracy achieved for speaker independent alphabet recognition, using 50 features, was 97.9%, which represents a new benchmark for this task. We also tested these methods with deliberate signal degradation using additive Gaussian noise and telephone band limiting and found that the recognition degrades gracefully and to a smaller degree than for control cases based on MFCC coefficients and delta cepstra terms.

This paper presents an investigation of non-uniform time sampling methods for spectral/temporal feature extraction for use in automatic speech recognition. In most current methods for signal modeling of speech information, “dynamic ” features are determined from frame-based parameters using a fixed time sampling, i.e., fixed block length and fixed block spacing. This work explores new methods in which block length and/or block spacing are variable. Three methods are suggested and each was tested with the TIMIT database using a standard HMM recognizer. Phone recognition experiments were conducted using the standard 39 phone set. The methods were also evaluated with various HMM model complexities. Experimental results indicated that none of the proposed nonuniform feature time sampling methods perform significantly better than fixed time sampling methods. However, the best results obtained with the front end are comparable to those obtained with current state-of-the-art systems. Also the performance of our monophone system surpasses that of most reported context-dependent monophone systems. 1.

Spectral feature computations continue to be a very difficult problem for accurate machine recognition of vowels especially in the presence of noise or for otherwise degraded acoustic signals. In this work, a new peak envelope method for vowel classification is developed, based on a missing frequency components model of speech recognition. According to this model, vowel recognition depends only on the location of spectral peaks. Also, smoothing and interpolation of the sampled spectra, performed in the cepstral analysis method commonly used in automatic speech recognition results in a loss of valuable information. The new method for feature extraction presented in this paper is based on minimum mean square error curve fitting of cosine-like basis vectors to all peaks in the speech spectrum. A mathematical model for smoothly tracking spectral envelopes using only spectral peak information and ignoring other parts of the spectrum is presented. A software algorithm for the model was developed and tested for various speaker types using a neural network classifier. Vowel classification experiments were conducted based on the features derived from the spectral peaks. The classification rates of the peak method under various signal to noise ratios was also evaluated. The basic conclusion is that the new features perform the same as cepstral features for clean speech, but have advantages when the signal is degraded by noise.

This paper presents speech signal modeling techniques which are well suited to high performance and robust isolated word recognition. Speech is encoded by a discrete cosine transform of its spectra, after several preprocessing steps. Temporal information is then also explicitly encoded into the feature set. We present a new technique for incorporating this temporal information as a function of the temporal position within each word. We tested features computed with this method using an alphabet recognition task based on the ISOLET database. The HTK toolkit was used to implement the isolated word recognizer with whole word HMM models. The best result obtained based on 50 features and speaker independent alphabet recognition was 98.0%. Gaussian noise was added to the original speech to simulate a noisy environment. We achieved a recognition accuracy of 95.8% at a SNR of 15 dB. We also tested our recognizer with simulated telephone quality speech by adding noise and band limiting the original speech. For this "telephone" speech, our recognizer achieved 89.6% recognition accuracy. The recognizer was also tested in a speaker dependent mode, resulting in a 97.4% accuracy on test data.

Spectral/temporal segment features are adapted for isolated word recognition and tested with the entire English alphabet set using Hidden Markov Models.The ISOLET database from OGI and the HTK toolkit from Cambridge university were used to test our feature extraction technique.With our feature set we were able to achieve 97.3% recognition accuracy on test data with one pass using a whole word based recognizer.Gaussian noise was also added to evaluate robustness of the feature set.We were able to obtain recognition accuracies of 49.6% and 84.3% at SNR of -10dB and 0dB, respectively.Linear discriminant analysis was also applied to the initial feature set for a number of feature configurations and noise levels but, generally, the performance was not improved.We conclude that the initial feature computations used are both very efficient (best results obtained with 50 total features) and robust in the presence of noise.