Context-adaptive pre-processing scheme for robust speech recognition in fast-varying noise environment

Based on the observation that dissimilar speech enhancement algorithms perform differently for different types of interference and noise conditions, we propose a context-adaptive speech pre-processing scheme, which performs adaptive selection of the most advantageous speech enhancement algorithm for each condition. The selection process is based on an unsupervised clustering of the acoustic feature space and a subsequent mapping function that identifies the most appropriate speech enhancement channel for each audio input, corresponding to unknown environmental conditions. Experiments performed on the MoveOn motorcycle speech and noise database validate the practical value of the proposed scheme for speech enhancement and demonstrate a significant improvement in terms of speech recognition accuracy, when compared to the one of the best performing individual speech enhancement algorithm. This is expressed as accuracy gain of 3.3% in terms of word recognition rate. The advance offered in the present work reaches beyond the specifics of the present application, and can be beneficial to spoken interfaces operating in fast-varying noise environments.     

The MoveOn database: motorcycle environment speech and noise database for command and control applications

The MoveOn speech and noise database was purposely designed and implemented in support of research on spoken dialogue interaction in a motorcycle environment. The distinctiveness of the MoveOn database results from the requirements of the application domain—an information support and operational command and control system for the two-wheel police force—and also from the specifics of the adverse open-air acoustic environment. In this article, we first outline the target application, motivating the database design and purpose, and then report on the implementation details. The main challenges related to the choice of equipment, the organization of recording sessions, and some difficulties that were experienced during this effort, are discussed. We offer a detailed account of the database statistics, the suggested data splits in subsets, and discuss results from automatic speech recognition experiments which illustrate the degree of complexity of the operational environment.     

A study of the downward flow of a liquid film along a vertical surface with attendant heat transfer

This report deals with a theoretical and experimental study concerning the measurement of local values of mean film thickness throughout the film length and with theoretical relations derived for determining the film thickness in the laminar-wave as well as in the turbulent region. The experimental studies have also covered local characteristics of wave motion on the film surface as well as the velocity field in the continuous layer, the local heat-transfer coefficients along the height of a vertical channel, and a critical relation for determining them has been derived.Translated from Inzhenerno-Fizicheskii Zhurnal, Vol. 20, No. 4, pp. 674–682, April, 1971.     

Wetting of a hot vertical surface by a flowing liquid film

A planar two-dimensional problem of the wetting of a dry heated vertical surface by a flowing liquid film was experimentally investigated. A model of the process was developed and the problem was numerically solved.Translated from Izhenerno-Fizicheskii Zhurnal, Vol. 14, No. 5, pp. 773–780, November, 1981.     

Calibration and measurement of dielectric properties of finitethickness composite sheets with open-ended coaxial sensors

The application of open-ended coaxial sensors for dielectric measurement of finite thickness composite sheets is studied. Expressions for calculation of the complex aperture admittance for two geometries are presented. These expressions are used to calculate the dielectric constant of infinite half-space as well as finite thickness slabs. A more efficient method of such calculations, using a personal computer, for low to medium loss dielectrics is demonstrated. The question of when a dielectric layer may be considered as infinitely thick is also addressed, and examples are presented. A different calibration technique (compared to the conventional ones) is described and successfully implemented. This calibration technique utilizes a dielectric sheet with known dielectric properties and thickness. Measurements for different airgaps between the open-ended coaxial line and the dielectric sheet are used to perform and enhance the calibration. The results of this calibration technique and several subsequent measurements are presented and discussed     

Processes of hydrodynamics and heat exchange in descending bubble flows

The gas content, hydraulic resistance, heat transfer, and structure of descending bubble flows are investigated in the regimes of concurrent flow and of hovering of the gas phase.Translated from Inzhenerno-Fizicheskii Zhurnal, Vol. 49, No. 2, pp. 181–189, August, 1985.     

Two-stage phone duration modelling with feature construction and feature vector extension for the needs of speech synthesis

We propose a two-stage phone duration modelling scheme, which can be applied for the improvement of prosody modelling in speech synthesis systems. This scheme builds on a number of independent feature constructors (FCs) employed in the first stage, and a phone duration model (PDM) which operates on an extended feature vector in the second stage. The feature vector, which acts as input to the first stage, consists of numerical and non-numerical linguistic features extracted from text. The extended feature vector is obtained by appending the phone duration predictions estimated by the FCs to the initial feature vector. Experiments on the American-English KED TIMIT and on the Modern Greek WCL-1 databases validated the advantage of the proposed two-stage scheme, improving prediction accuracy over the best individual predictor, and over a two-stage scheme which just fuses the first-stage outputs. Specifically, when compared to the best individual predictor, a relative reduction in the mean absolute error and the root mean square error of 3.9% and 3.9% on the KED TIMIT, and of 4.8% and 4.6% on the WCL-1 database, respectively, is observed.     

Phonetic segmentation using multiple speech features

In this paper we propose a method for improving the performance of the segmentation of speech waveforms to phonetic units. The proposed method is based on the well known Viterbi time-alignment algorithm and utilizes the phonetic boundary predictions from multiple speech parameterization techniques. Specifically, we utilize the most appropriate, with respect to boundary type, phone transition position prediction as initial point to start Viterbi time-alignment for the prediction of the successor phonetic boundary. The proposed method was evaluated on the TIMIT database, with the exploitation of several, well known in the area of speech processing, Fourier-based and wavelet-based speech parameterization algorithms. The experimental results for the tolerance of 20 milliseconds indicated an improvement of the absolute segmentation accuracy of approximately 0.70%, when compared to the baseline speech segmentation scheme.     

Wavelet packet approximation of critical bands for speaker verification

Exploiting the capabilities offered by the plethora of existing wavelets, together with the powerful set of orthonormal bases provided by wavelet packets, we construct a novel wavelet packet-based set of speech features that is optimized for the task of speaker verification. Our approach differs from previous wavelet-based work, primarily in the wavelet-packet tree design that follows the concept of critical bands, as well as in the particular wavelet basis function that has been used. In comparative experiments, we investigate several alternative speech parameterizations with respect to their usefulness for differentiating among human voices. The experimental results confirm that the proposed speech features outperform Mel-Frequency Cepstral Coefficients (MFCC) and previously used wavelet features on the task of speaker verification. A relative reduction of the equal error rate by 15%, 15% and 8% was observed for the proposed speech features, when compared to the wavelet packet features introduced by Farooq and Datta, the MFCC of Slaney, and the subband based cepstral coefficients of Sarikaya et al., respectively.