Gopalakrishnan et al [1] described a method called "growth transform" to optimize rational functions over a domain, which has been found useful to train discriminatively Hidden Markov Models(HMM) in speech r...
详细信息
作者：
R.I. DamperImage
Speech and Intelligent Systems ISIS Research Group Department of Electronics and Computer Science University of Southampton Southampton UK Center for Spoken Language Understanding
Department of Computer Science and Engineering Oregon Graduate Institute of Science and Technology Portland OR USA
Important aspects of the voiced/unvoiced categorization of synthetic syllable-initial stop consonants are reproduced by a two stage biocybernetic simulation of the auditory system. This behavior is emergent - it is no...
详细信息
Important aspects of the voiced/unvoiced categorization of synthetic syllable-initial stop consonants are reproduced by a two stage biocybernetic simulation of the auditory system. This behavior is emergent - it is not explicitly programmed into the model - and no fine timing information is necessary. Unlike real (human and animal) listeners, the computational auditory model can be systematically manipulated and probed to determine the basis of its behavior. This reveals the importance of the region of first formant onset to the perception of voicing for these stimuli. Spectral analysis of this region in the raw stimuli show that processing by the first stage of the model, mimicking the functions of the peripheral auditory system, is not essential to the observed behavior. Thus, in this case at least, the phonetic perception of voicing is directly recoverable from both acoustic and auditory representations of the stimuli.
Detection of speech in noisy recordings becomes a challenging problem when the noise does not follow the usual whiteness, stationarity and high signal-to-noise ratio assumptions. A robust speech detector can affect si...
详细信息
Detection of speech in noisy recordings becomes a challenging problem when the noise does not follow the usual whiteness, stationarity and high signal-to-noise ratio assumptions. A robust speech detector can affect significantly the performance of several speechprocessing tasks, such as endpoint detection, segmentation, and finally recognition, if we deal with real life data, as opposed to laboratory or controlled environment recordings. The detector proposed is based on a Gaussianity test that employs third-order cumulants of the data to decide on the binary hypotheses of noise only versus speech plus noise. speech intervals are detected by exploiting the third-order information present in the speech signal. The detector can handle a large family of additive noises, thanks to its third-order statistics basis. The sample-adaptive and decision feedback variations proposed, provide the detector with a tracking ability both with respect to the time variations of speech and the possible nonstationarity of noise. Experiments carried out using real data, recorded in a moving car interior, show satisfactory performance of the proposed algorithms down to -6 dB signal-to-noise ratio.< >
An overview is presented of results obtained in listeners with real and simulated impairments. Spectral processing is assessed by psychoacoustical tuning curves and growth-of-masking functions; temporal processing is ...
详细信息
An overview is presented of results obtained in listeners with real and simulated impairments. Spectral processing is assessed by psychoacoustical tuning curves and growth-of-masking functions; temporal processing is assessed by temporal integration and gap detection thresholds. When comparisons are made to normal listeners tested in the quiet, impaired listeners generally show deficits on all these tasks. When the comparisons are made to simulated impairments, some impaired listeners show no deficits, whereas others still show deficits. These results indicate that abnormal intensity perception is responsible for some, but not all, of impaired listeners' apparent deficits in spectral and temporal processing. In many cases, however, it appears that spectral and temporal processing, per se, are altered in the impaired auditory system.< >
作者：
Robert L. MercerSpeech-Processing Group
Computer Science Department International Business Machines Corporation Thomas J. Watson Research Center Yorktown Heights New York 10598
We obtain a solution of the Dirac equation in the presence of the electromagnetic field of a complex nucleus by means of coupled-channel partial wave analysis using a new method in which the asymptotic solutions of th...
We obtain a solution of the Dirac equation in the presence of the electromagnetic field of a complex nucleus by means of coupled-channel partial wave analysis using a new method in which the asymptotic solutions of the coupled radial wave equations include all electromagnetic couplings. A compu er program employing this method is used to determine the importance of dispersion effects in the scattering of 250 MeV electrons from Ca40 and Ca44. We find the dispersion effects to be less than 1% for angles below 90° (i.e., considerably less than experimental error over the range investigated experimentally), thus supporting the view that the difference in the differential cross sections from Ca40 and Ca44 arises primarily from a difference in the ground state charge distributions of the two isotopes.
Discrepancies among experiments and theory on electron scattering from oriented holmium are partially resolved. An estimate is presented which suggests that the distorted-wave Born-approximation orientation effect cal...
Discrepancies among experiments and theory on electron scattering from oriented holmium are partially resolved. An estimate is presented which suggests that the distorted-wave Born-approximation orientation effect calculated by Wright is too large by about a factor of 2. Distorted-wave Born-approximation calculations (made with a coupled-channel program) are presented which confirm this suggestion. They agree well with the Stanford data for orientation perpendicular to the scattering plane. The previous discrepancy for orientation along the recoil-momentum direction is reduced, but is not removed. The sensitivity of these results to the charge shape is examined although a fit to the data is not made. Results are given of a complete coupled-channel calculation for the first three nuclear states. Suggestions are made for future work, and cross sections and orientation effects for energyresolved scattering from holmium at 200 MeV are given.
Finding knowledge – or meaning – in data is the goal of every knowledge d- covery e?ort. Subsequent goals and questions regarding this knowledge di?er amongknowledgediscovery(KD) projectsandapproaches. Onecentralque...
详细信息
ISBN:
(数字)9783540476986
ISBN:
(纸本)9783540476979
Finding knowledge – or meaning – in data is the goal of every knowledge d- covery e?ort. Subsequent goals and questions regarding this knowledge di?er amongknowledgediscovery(KD) projectsandapproaches. Onecentralquestion is whether and to what extent the meaning extracted from the data is expressed in a formal way that allows not only humans but also machines to understand and re-use it, i. e. , whether the semantics are formal semantics. Conversely, the input to KD processes di?ers between KD projects and approaches. One central questioniswhetherthebackgroundknowledge,businessunderstanding,etc. that the analyst employs to improve the results of KD is a set of natural-language statements, a theory in a formal language, or somewhere in between. Also, the data that are being mined can be more or less structured and/or accompanied by formal semantics. These questions must be asked in every KD e?ort. Nowhere may they be more pertinent, however, than in KD from Web data (“Web mining”). Thisis due especially to the vast amounts and heterogeneity of data and ba- ground knowledge available for Web mining (content, link structure, and - age), and to the re-use of background knowledge and KD results over the Web as a global knowledge repository and activity space. In addition, the (Sem- tic) Web can serve as a publishing space for the results of knowledge discovery from other resources, especially if the whole process is underpinned by common ontologies.
This book constitutes the proceedings of the Third International Conference of the CLEF Initiative, CLEF 2012, held in Rome, Italy, in September 2012. The 14 papers and 3 poster abstracts presented were carefully revi...
详细信息
ISBN:
(数字)9783642332470
ISBN:
(纸本)9783642332463
This book constitutes the proceedings of the Third International Conference of the CLEF Initiative, CLEF 2012, held in Rome, Italy, in September 2012.
The 14 papers and 3 poster abstracts presented were carefully reviewed and selected for inclusion in this volume. Furthermore, the books contains 2 keynote papers. The papers are organized in topical sections named: benchmarking and evaluation initiatives; information access; and evaluation methodologies and infrastructure.
暂无评论