Speaker-independent Vowel Recognition Research Articles

METHOD FOR ANALYSING SIGNALS CONTAINING PULSES

The invention provides a method for analysing an input signal having an input frequency bandwidth. The method comprises providing at Ieast one fre quency-bandwidth limited portion of the input signal. For each frequency-bandwidth limited portion of the input signal the durations of half-periods and signal excursions during respective half-periods are determined. Based on the signal excursions and corresponding half-periods a quality of the input signal is determined. The determined signal quality can be a vowel in a 10 speech signal or a quality related to a condition of an industrial product. The method provides speaker independent vowel recognition, and even whis pered vowels can be recognised.

Pluralizing simple similarity based on a natural observation method of normal type, with an application to speaker-independent vowel recognition

Pluralizing simple similarity based on a natural observation method of normal type, with an application to speaker-independent vowel recognition

Flexible vowel recognition by the generation of dynamic coherence in oscillator neural networks: speaker-independent vowel recognition

Flexible vowel recognition by the generation of dynamic coherence in oscillator neural networks: speaker-independent vowel recognition

Flexible vowel recognition by the generation of dynamic coherence in oscillator neural networks: speaker-independent vowel recognition.

We propose a new model for speaker-independent vowel recognition which uses the flexibility of the dynamic linking that results from the synchronization of oscillating neural units. The system consists of an input layer and three neural layers, which are referred to as the A-, B- and C-centers. The input signals are a time series of linear prediction (LPC) spectrum envelopes of auditory signals. At each time-window within the series, the A-center receives input signals and extracts local peaks of the spectrum envelope, i.e., formants, and encodes them into local groups of independent oscillations. Speaker-independent vowel characteristics are embedded as a connection matrix in the B-center according to statistical data of Japanese vowels. The associative interaction in the B-center and reciprocal interaction between the A- and B-centers selectively activate a vowel as a global synchronized pattern over two centers. The C-center evaluates the synchronized activities among the three formant regions to give the selective output of the category among the five Japanese vowels. Thus, a flexible ability of dynamical linking among features is achieved over the three centers. The capability in the present system was investigated for speaker-independent recognition of Japanese vowels. The system demonstrated a remarkable ability for the recognition of vowels very similar to that of human listeners, including misleading vowels. In addition, it showed stable recognition for unsteady input signals and robustness against background noise. The optimum condition of the frequency of oscillation is discussed in comparison with stimulus-dependent synchronizations observed in neurophysiological experiments of the cortex.

Growing and pruning neural tree networks

A pattern classification method called neural tree networks (NTNs) is presented. The NTN consists of neural networks connected in a tree architecture. The neural networks are used to recursively partition the feature space into subregions. Each terminal subregion is assigned a class label which depends on the training data routed to it by the neural networks. The NTN is grown by a learning algorithm, as opposed to multilayer perceptrons (MLPs), where the architecture must be specified before learning can begin. A heuristic learning algorithm based on minimizing the L1 norm of the error is used to grow the NTN. It is shown that this method has better performance in terms of minimizing the number of classification errors than the squared error minimization method used in backpropagation. An optimal pruning algorithm is given to enhance the generalization of the NTN. Simulation results are presented on Boolean function learning tasks and a speaker independent vowel recognition task. The NTN compares favorably to both neural networks and decision trees.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

On the use of line spectral frequency parameters for speech recognition

The line spectral frequency (LSF) representation has been proposed by Itakura [l] as an alternative linear prediction (LP) parametric representation. In the context of speech coding, it has been shown [2-61 that this representation has better quantization properties than the other LP parametric representations (such as log area ratios and reflection coefficients). The LSF representation is capable of reducing the bit-rate by 25-30% for transmitting the LP information without degrading the quality of synthesized speech [4,5]. Our interest in LSF representation has been to see whether we can obtain a similar advantage from this representation for speech recognition. For this, we studied this representation in our earlier paper for the recognition of steady-state vowel frames in the speaker-dependent mode using the minimum distance classifier [7]. Though the LSF representation resulted in good performance [7], the scope of these results was very limited. The aim of the present paper is to extend the use of the LSF representation for more general speech recognition systems and to widen the scope of its results. (Some of these results have been reported earlier in a conference [8].) For this, we study here this representation in both the speaker-dependent and the speaker-independent modes for the hidden Markov model (HMM)-based isolated word recognition systems. Since the HMM-based speech recognizers use the maximum likelihood decision rule for recognition, we also report here the results for the speaker-&pendent and the speaker-independent vowel recognition experiments using the maximum likelihood classifier, In the present paper, we compare the performance of

A Method for Designing Neural Networks Using Nonlinear Multivariate Analysis: Application to Speaker-Independent Vowel Recognition

A nonlinear multiple logistic model and multiple regression analysis are described as a method for determining the weights for two-layer networks and are compared to error backpropagation. We also provide a method for constructing a three-layer network whose semilinear middle units are primarily provided to discriminate two categories. Experimental results on speaker-independent vowel recognition show that both multivariate methods provide stable weights with fewer iterations than backpropagation training started with random initial weights, but with slightly inferior performance. Backpropagation training with initial weights determined by a multiple logistic model after introduction of data distribution information gives a recognition rate of 98.2%, which is significantly better than average backpropagation with random initial weights.

A performance comparison of trained multilayer perceptrons and trained classification trees

The important differences between multilayer perceptrons and classification trees are considered. A number of empirical tests on three real-world problems in power-system load forecasting, power-system security prediction, and speaker-independent vowel recognition are presented. The load-forecasting problem, which is partially a regression problem, uses past trends to predict the critical needs of future power generation. The power-security problem uses the classifier as an interpolator of previously known states of the system. The vowel-recognition problem is representative of the difficulties in automatic speech recognition caused by variability across speakers and phonetic context. In all cases even with various sizes of training sets, the multilayer perceptron performed as well as or better than the trained classification trees. It is therefore concluded that there is not enough theoretical basis to demonstrate clear-cut superiority of one technique over the other. >

Analysis and recognition of isolated putonghua vowels by Karhunen-Loève transformation techniques

A systematic study on a speaker-independent vowel recognition model has been performed. Karhunen-Loève Transformation (KLT), or Principal Component Analysis, technique was applied subsequent to a spectral analysis of the speech signal by 18 non-overlapping critical-band filters. Four experiments have been conducted using selected segments of 8 isolated Putonghua (Mandarin) vowels, spoken twice in 5 tones by 38 females and 13 males. The first experiment uses the same speech sample in training and testing to evaluate the effects of KLT, speaker normalization, distance metric and number of vowel classes. A modified Mahalanobis distance coupled with a 7-class condition was found to give the best performance. In the next experiment, one sample was used to train the model, and another trial of the same speech, spoken by the same group of speakers, was used to test it. It was found that, in general, a sex-specific and tone-specific procedure could be avoided without significant loss in performance. The third experiment repeatedly trained the model with 50 speakers and tested it wiht the remaining one until all 51 speakers had been tested. Under this stringent condition, an average recognition rate of 88.2% was achieved using only 4 classificatory dimensions. In the last experiment, all segments of a vowel were labelled using the most stringent conditions. The model was confirmed to perform well for one male and one female speaker selected at random. Also, the vowel that had caused the greatest confusion was found to be well recognized when treated as an allophone of another vowel. Finally, the possibility of extending the present technique to diphthong recognition is discussed together with some preliminary results.