Peter V. De Souza

Speech recognizer having a speech coder for an acoustic match based on context-dependent speech-transition acoustic models

A speech coding apparatus compares the closeness of the feature value of a feature vector signal of an utterance to the parameter values of prototype vector signals to obtain prototype match scores for the feature vector signal and each prototype vector signal. The speech coding apparatus stores a plurality of speech transition models representing speech transitions. At least one speech transition is represented by a plurality of different models. Each speech transition model has a plurality of model outputs, each comprising a prototype match score for a prototype vector signal. Each model output has an output probability. A model match score for a first feature vector signal and each speech transition model comprises the output probability for at least one prototype match score for the first feature vector signal and a prototype vector signal. A speech transition match score for the first feature vector signal and each speech transition comprises the best model match score for the first feature vector signal and all speech transition models representing the speech transition. The identification value of each speech transition and the speech transition match score for the first feature vector signal and each speech transition are output as a coded utterance representation signal of the first feature vector signal.

Edge detection using sliding statistical tests

Abstract The problem discussed is that of detecting edges in one-dimensional image profiles, with particular attention being paid to the case in which there is prior information available regarding the scene. Five sliding statistical tests are presented which often display well-defined turning points in the vicinity of edges, thereby enabling edges to be located. Some of the tests are applicable to the case of detecting edges between objects of different intensity, and others are applicable to the case of textures where there may be no difference in average intensity on each side of the edge.

Texture recognition via autoregression

Abstract This article considers the image processing problem of texture recognition. It is shown that a chi-square test based upon a two-dimensional autoregressive model can be derived and can be used to test for differences between certain types of micro-textures. The chi-square test cannot be used with macro-textures, and another autoregressive-based distance measure is derived which is more suitable for these cases. It is shown experimentally that this distance measure affords a reliable means of classifying a broad class of micro- and macro-textures using a nearest-neighbour type of approach.

Automatic rib detection in chest radiographs

Abstract A detailed algorithm is presented for automatic detection of posterior (dorsal) ribs in posterior/anterior chest radiographs. It is entirely automatic and includes algorithms for locating the lung fields and the lung boundary. Written in PL/I for an IBM 3031, it requires about 8 sec to process a 400 × 400 digitized full chest radiograph which is significantly faster than previously published results. The reason for the efficiency can be attributed to the fact that no two-dimensional image processing is performed; it works instead by locating the ribs on a small set of one-dimensional sections taken through the lung fields. Curves are then fitted through these locations to represent the rib edges. The detection of anterior (ventral) ribs is also discussed.

Labelling speech using context-dependent acoustic prototypes

The present invention relates to labelling of speech in a context-dependent speech recognition system. When labelling speech using context-dependent prototypes the phone context of a frame of speech needs to be aligned with the appropriate acoustic parameter vector. Since aligning a large amount of data is difficult if based upon arc ranks, the present invention aligns the data using context-independent acoustic prototypes. The phonetic context of each phone of the data is known. Therefore after the alignment step the acoustic parameter vectors are tagged with a corresponding phonetic context. Context-dependent prototype vectors exists for each label. For all labels the context-dependent prototype vectors having the same phonetic context as the tagged acoustic parameter vector are determined. For each label the probability of achieving the tagged acoustic parameter vector is determined given each of the context-dependent label prototype vectors having the same phonetic context as the tagged acoustic parameter vector. The label with the highest probability is associated with the context-dependent acoustic parameter vector.

Speech recognition with continuous-parameter hidden Markov models

Abstract The acoustic modeling problem in automatic speech recognition is examined from an information-theoretic point of view. This problem is to design a speech-recognition system which can extract from the speech waveform as much information as possible about the corresponding word sequence. The information extraction process is broken down into two steps: a signal-processing step which converts a speech waveform into a sequence of information-bearing acoustic feature vectors, and a step which models such a sequence. We are primarily concerned with the use of hidden Markov models to model sequences of feature vectors which lie in a continuous space. We explore the trade-off between packing information into such sequences and being able to model them accurately. The difficulty of developing accurate models of continuous-parameter sequences is addressed by investigating a method of parameter estimation which is designed to cope with inaccurate modeling assumptions.

A note on a random walk model for texture analysis

Abstract Wechsler and Citron recently published a random walk model with applications in texture analysis. It is shown in the current note that their chi-square test of homogeneity based on this model is misleading.