The Experts below are selected from a list of 19266 Experts worldwide ranked by ideXlab platform
Ugo Vaccaro - One of the best experts on this subject based on the ideXlab platform.
-
an information theoretic approach to Probability Mass Function truncation
International Symposium on Information Theory, 2019Co-Authors: Ferdinando Cicalese, Luisa Gargano, Ugo VaccaroAbstract:Given a discrete random variable X that takes values in a finite set χ according to a Probability Mass Function (pmf) P, a truncated pmf Q of P is a conditional pmf that results from restricting the domain of X to some subset of χ. Truncated pmf arise in several problems of statistics and Probability. In this paper, we propose and analyze a few criteria to truncate pmf’s so that the truncated one is as much close as possible to the original pmf, under different information theoretic measures of distance.
-
ISIT - An Information Theoretic Approach to Probability Mass Function Truncation
2019 IEEE International Symposium on Information Theory (ISIT), 2019Co-Authors: Ferdinando Cicalese, Luisa Gargano, Ugo VaccaroAbstract:Given a discrete random variable X that takes values in a finite set χ according to a Probability Mass Function (pmf) P, a truncated pmf Q of P is a conditional pmf that results from restricting the domain of X to some subset of χ. Truncated pmf arise in several problems of statistics and Probability. In this paper, we propose and analyze a few criteria to truncate pmf’s so that the truncated one is as much close as possible to the original pmf, under different information theoretic measures of distance.
Farzaneh Ahmadi - One of the best experts on this subject based on the ideXlab platform.
-
spectral enhancement of whispered speech based on Probability Mass Function
International Conference on Telecommunications, 2010Co-Authors: Hamid Sharifzadeh, Ian Mcloughlin, Farzaneh AhmadiAbstract:Whispered speech can be effectively used for quiet and private communications over mobile phones and is also the communication means for ENT patients under a regime of voice rest. The reconstruction of natural sounding speech from such whispers can be useful for several types of application across different scientific fields ranging from communications to biomedical engineering. Despite the useful applications for a such technology, the reconstruction of natural speech from whispers has received relatively little research effort to date. This paper presents novel methods for spectral enhancement and formant smoothing with the aim of attaining more natural sounding speech within the reconstruction process. The proposed approach uses a Probability Mass-density Function to identify a reliable formant trajectory through whispers and apply vocal modifications accordingly. Subjective evaluation experiments were performed, and are reported, to assess the performance of the techniques. A method for the near real-time conversion of whispers to normal phonated speech through a modified CELP codec has been discussed in our previously published work which, the proposed formant modification approach in this paper builds upon.
-
AICT - Spectral Enhancement of Whispered Speech Based on Probability Mass Function
2010 Sixth Advanced International Conference on Telecommunications, 2010Co-Authors: Hamid Sharifzadeh, Ian Mcloughlin, Farzaneh AhmadiAbstract:Whispered speech can be effectively used for quiet and private communications over mobile phones and is also the communication means for ENT patients under a regime of voice rest. The reconstruction of natural sounding speech from such whispers can be useful for several types of application across different scientific fields ranging from communications to biomedical engineering. Despite the useful applications for a such technology, the reconstruction of natural speech from whispers has received relatively little research effort to date. This paper presents novel methods for spectral enhancement and formant smoothing with the aim of attaining more natural sounding speech within the reconstruction process. The proposed approach uses a Probability Mass-density Function to identify a reliable formant trajectory through whispers and apply vocal modifications accordingly. Subjective evaluation experiments were performed, and are reported, to assess the performance of the techniques. A method for the near real-time conversion of whispers to normal phonated speech through a modified CELP codec has been discussed in our previously published work which, the proposed formant modification approach in this paper builds upon.
Ferdinando Cicalese - One of the best experts on this subject based on the ideXlab platform.
-
an information theoretic approach to Probability Mass Function truncation
International Symposium on Information Theory, 2019Co-Authors: Ferdinando Cicalese, Luisa Gargano, Ugo VaccaroAbstract:Given a discrete random variable X that takes values in a finite set χ according to a Probability Mass Function (pmf) P, a truncated pmf Q of P is a conditional pmf that results from restricting the domain of X to some subset of χ. Truncated pmf arise in several problems of statistics and Probability. In this paper, we propose and analyze a few criteria to truncate pmf’s so that the truncated one is as much close as possible to the original pmf, under different information theoretic measures of distance.
-
ISIT - An Information Theoretic Approach to Probability Mass Function Truncation
2019 IEEE International Symposium on Information Theory (ISIT), 2019Co-Authors: Ferdinando Cicalese, Luisa Gargano, Ugo VaccaroAbstract:Given a discrete random variable X that takes values in a finite set χ according to a Probability Mass Function (pmf) P, a truncated pmf Q of P is a conditional pmf that results from restricting the domain of X to some subset of χ. Truncated pmf arise in several problems of statistics and Probability. In this paper, we propose and analyze a few criteria to truncate pmf’s so that the truncated one is as much close as possible to the original pmf, under different information theoretic measures of distance.
Mustafa Suphi Erden - One of the best experts on this subject based on the ideXlab platform.
-
Probability Mass Function distance approach for fast speaker diarization
Signal Processing and Communications Applications Conference, 2017Co-Authors: Levent M Arslan, Gokce Sarar, Sedat Demirbag, Mustafa Suphi ErdenAbstract:In this paper, a new method for speaker diarization is presented. Using spectral features, vector quantization is applied over all audio data. Frames are labelled with the id of the closest codeword. Based on the histogram of frame ids, a Probability Mass Function is estimated for each speech segment. Sequential clustering is implemented based on the distances between Probability Mass Functions. Prosodic parameters are incorporated in order to determine whether there is speaker change within each segment. When applied to real life call center conversations, proposed system achieves 17% relative improvement in terms of diarization error rate compared to a standard open source toolkit. Besides, in terms of processing times, 7 times faster processing is achieved with respect to reference toolkit.
-
SIU - Probability Mass Function distance approach for fast speaker diarization
2017 25th Signal Processing and Communications Applications Conference (SIU), 2017Co-Authors: Levent M Arslan, Gokce Sarar, Sedat Demirbag, Mustafa Suphi ErdenAbstract:In this paper, a new method for speaker diarization is presented. Using spectral features, vector quantization is applied over all audio data. Frames are labelled with the id of the closest codeword. Based on the histogram of frame ids, a Probability Mass Function is estimated for each speech segment. Sequential clustering is implemented based on the distances between Probability Mass Functions. Prosodic parameters are incorporated in order to determine whether there is speaker change within each segment. When applied to real life call center conversations, proposed system achieves 17% relative improvement in terms of diarization error rate compared to a standard open source toolkit. Besides, in terms of processing times, 7 times faster processing is achieved with respect to reference toolkit.
Ramalingam Shanmugam - One of the best experts on this subject based on the ideXlab platform.
-
A Type-1 Imbalanced Bivariate Poisson Distribution Demystifies Patient’s Phobia Visiting Physician Often and Its Implications
Journal of Statistical Theory and Practice, 2018Co-Authors: Ramalingam ShanmugamAbstract:In this article, a new bivariate Poisson distribution, called the type - 1 imbalanced bivariate Poisson distribution, is introduced for dependence modeling among the random number of visits made by a patient and the number of prescriptions written by a physician. By utilizing the proposed model, the article discovers patterns on the implications of the over-visits made by the patients. This new discrete bivariate Poisson Probability Mass Function is quite interesting and useful to the healthcare researchers. Its statistical properties are derived. The concepts and methodology around its imbalance parameter, $$ \phi $$ ϕ , are constructed and illustrated using the Australian Health Survey data for 1997–1998. The data analytic results in the illustration demystify the implications when the patients make more visits to the physician.
