https://www.cs.ubc.ca/~murphyk/Teaching/CS540-Spring10/projects/Yu-hsmm09.pdf

Hidden semi-Markov models

Abstruct- We have compared the performance of four approaches for automatic language identification of speech utterances: Gaussian mixture model (GMM) classification; single-language phone recognition followed by languagedependent, interpolated n-gram language modeling (PRLM); parallel PRLM, which uses multiple single-language phone recognizers, each trained in a different language; and languagedependent parallel phone recognition (PPR). These approaches, which span a wide range of training requirements and levels of recognition complexity, were evaluated with the Oregon Graduate Institute Multi-Language Telephone Speech Corpus. Systems containing phone recognizers performed better than the simpler GMM classifier. The top-performing system was parallel PRLM, which exhibited an error rate of 2% for 45-s utterances and 5% for 10-s utterances in two-language, closed-set, forcedchoice classification. The error rate for 11-language, closed-set, forced-choice classification was 11 % for 45-s utterances and 21% for 10-s utterances.

/pdf/comparison-of-four-approaches-to-automatic-language-1d71h1ublh.pdf

Comparison of four approaches to automatic language identification of telephone speech

Gas leaks can cause major incidents resulting in both human injuries and financial losses. To avoid such situations, a considerable amount of effort has been devoted to the development of reliable techniques for detecting gas leakage. As knowing about the existence of a leak is not always enough to launch a corrective action, some of the leak detection techniques were designed to allow the possibility of locating the leak. The main purpose of this paper is to identify the state-of-the-art in leak detection and localization methods. Additionally we evaluate the capabilities of these techniques in order to identify the advantages and disadvantages of using each leak detection solution.

https://www.aut.upt.ro/~pal-stefan.murvay/papers/survey_gas_leak_detection_localization_techniques.pdf

A survey on gas leak detection and localization techniques

Methods are presented for adaptively generating wavelet templates for signal representation and classification using neural networks. Different network structures and energy functions are necessary and are given for representation and classification. The idea is introduced of a "super-wavelet," a linear combination of wavelets that itself is treated as a wavelet. The super-wavelet allows the shape of the wavelet to adapt to a particular problem, which goes beyond adapting parameters of a fixed-shape wavelet. Simulations are given for 1-D signals, with the concepts extendable to imagery. Ideas are discussed for applying the concepts in the paper to phoneme and speaker recognition.

Neural network adaptive wavelets for signal representation and classification

Recent advances in speaker recognition

A text-independent speaker verification system based on an adaptive vocal tract model which emulates the vocal tract of the speaker is described. Each speaker is represented by a set of feature vectors derived from speech segments belonging to different classes of phonemes. Linear predictive hidden Markov modeling and maximum-likelihood Viterbi decoding are applied to a speech utterance to obtain different classes of phonemes pronounced by a speaker. It is shown that different classes of phonemes are not equally effective in discriminating between speakers and that verification performance can be considerably improved by separately classifying speech segments representing each broad phonetic category as belonging to an impostor or as belonging to the true speaker. A weighted linear combination of scores for individual categories can be used as the final verification score. The weights are chosen to reflect the effectiveness of particular classes of phonemes in discriminating between speakers and are adjusted to maximize the verification performance. >

Variable parameter speaker verification system based on hidden Markov modeling

An automatic language identification system which makes use of several language specific features is described. The system concurrently utilizes features associated with two methodologies, the hidden Markov model, (HMM) and language-specific pitch contours. Experimental results show that transition probabilities and pitch contours show differences between the languages. However, each of the described criteria will not give in every case a definitive answer, but will lead in the correct direction. Therefore, a voting classifier should be used to combine the results from each of the criteria. >

An automatic language identification system

An approach and a solution to the continuous leak monitoring problem in underground gas pipelines are presented. This approach places permanent monitoring units along the pipeline. These units detect acoustic signals in the pipeline and discriminate leak sounds from other man-made or natural nonleak sounds that can occur. The system uses the kNN classifier as the detector with LPC (linear predictive coding) cepstrums as signal features. To increase system performance, pipeline effects on acoustic signals were taken into account during the classifier training phase. Each unit can detect 1/4-in-diameter leaks from a distance of 300 m, yielding 600 m as the maximum distance between units. >

Leak monitoring system for gas pipelines

Text-independent speaker verification systems typically depend upon averaging over a long utterance to obtain a feature set for classification. However, not all speech is equally suited to the task of speaker verification. An approach to text-independent speaker verification that uses a two-stage classifier is presented. The first stage consists of a speaker-independent phoneme detector trained to recognize a phoneme that is distinctive from speaker to speaker. The second stage is trained to recognize the frames of speech from the target speaker that are admitted by the phoneme detector. A common feature vector based on the linear predictive coding (LPC) cepstrum is projected in different directions for each of these pattern recognition tasks. Results of tests using the described speaker verification system are shown. >

Phoneme based speaker verification

Hidden Markov models (HMMs) have been used to model speech in many areas of speech processing. One characteristic of the HMM is that the probability of time spent in a particular state, or state occupancy, is geometrically distributed. This, however, becomes a serious limitation and results in inaccurate modeling when the HMMs are used for phoneme recognition. The authors use hidden semi-Markov models (HSMM) to overcome the above limitation. Semi-Markov models are a more general class of Markov chains in which the state occupancy can be explicitly modeled by an arbitrary probability mass distribution. The authors use non-parametric distributions to describe the state occupancies instead of parametric distributions such as gamma. Poisson or binomial, as analysis of actual data shows that the duration of some phonemes could not be approximated by any of the above. Preliminary tests conducted using only the linear prediction coding (LPC) cepstrum as features have shown that the use of HSMM increased the phoneme recognition accuracy to 53.7% from the 48.4% obtained using an HMM. >

M. Savic

Papers

Variable parameter speaker verification system based on hidden Markov modeling

An automatic language identification system

Leak monitoring system for gas pipelines

Phoneme based speaker verification

Use of semi-Markov models for speaker-independent phoneme recognition