Exploració per autor "Hernando Pericás, Francisco Javier"
Ara es mostren els items 38-57 de 133
-
Feature classification by means of Deep Belief Networks for speaker recognition
(Institute of Electrical and Electronics Engineers (IEEE), 2015)
Text en actes de congrés
Accés restringit per política de l'editorialIn this paper, we propose to discriminatively model target and impostor spectral features using Deep Belief Networks (DBNs) for speaker recognition. In the feature level, the number of impostor samples is considerably ... -
Frequency and time filtering of filter-bank energies for HMM speech recognition
(H. TIMOTHY BRUMMELL, WILLIAM IDSARDI CITATION DELAWARE, NEW CASTLE, DELAWARE, 1996)
Comunicació de congrés
Accés restringit per política de l'editorialIn speech recognition, a discriminative frequency weighting can be achieved by decorrelating the frequency sequence of log mel-scaled filter-bank energies with a computationally inexpensive filter. We show how the spectral ... -
From features to speaker vectors by means of restricted Boltzmann machine adaptation
(2016)
Comunicació de congrés
Accés obertRestricted Boltzmann Machines (RBMs) have shown success in different stages of speaker recognition systems. In this paper, we propose a novel framework to produce a vector-based representation for each speaker, which will ... -
GCC-PHAT based head orientation estimation
(2012)
Text en actes de congrés
Accés obertThis work presents a novel two-step algorithm to estimate the orientation of speakers in a smart-room environment equipped with microphone arrays. First the position of the speaker is estimated by the SRP-PHAT algorithm, ... -
Global impostor selection for DBNs in multi-session i-vector speaker recognition
(2014-11-19)
Article
Accés restringit per política de l'editorialAn effective global impostor selection method is proposed in this paper for discriminative Deep Belief Networks (DBN) in the context of a multi-session i-vector based speaker recognition. The proposed method is an ... -
i-Vector modeling with deep belief networks for multi-session speaker recognition
(2014)
Text en actes de congrés
Accés restringit per política de l'editorialIn this paper we propose an impostor selection method for a Deep Belief Network (DBN) based system which models i-vectors in a multi-session speaker verification task. In the proposed method, instead of choosing a ... -
I-vector transformation using k-nearest neighbors for speaker verification
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Text en actes de congrés
Accés restringit per política de l'editorialProbabilistic Linear Discriminant Analysis (PLDA) is the most efficient backend for i-vectors. However, it requires labeled background data which can be difficult to access in practice. Unlike PLDA, cosine scoring avoids ... -
Improving detection of acoustic events using audiovisual data and feature level fusion
(2009)
Text en actes de congrés
Accés obertThe detection of the acoustic events (AEs) that are naturally produced in a meeting room may help to describe the human and social activity that takes place in it. When applied to spontaneous recordings, the detection ... -
Improving i-Vector and PLDA based speaker clustering with long-term features
(International Speech Communication Association (ISCA), 2016)
Text en actes de congrés
Accés restringit per política de l'editoriali-vector modeling techniques have been successfully used for speaker clustering task recently. In this work, we propose the extraction of i-vectors from short-and long-term speech features, and the fusion of their PLDA ... -
Improving the robustness of the usual fbe-based asr front-end
(Mergablum, 2000)
Text en actes de congrés
Accés obertAll speech recognition systems require some form of signal representation that parametrically models the temporal evolution of the spectral envelope. Current parameterizations involve, either explicitly or implicitly, ... -
Informe proyecto SARAI
(2013-03-05)
Report de recerca
Accés obert -
Jitter and Shimmer measurements for speaker diarization
(2014)
Text en actes de congrés
Accés obertJitter and shimmer voice quality features have been successfully used to characterize speaker voice traits and detect voice pathologies. Jitter and shimmer measure variations in the fundamental frequency and amplitude ... -
Language modelling for speaker diarization in telephonic interviews
(Elsevier, 2023-03)
Article
Accés obertThe aim of this paper is to investigate the benefit of combining both language and acoustic modelling for speaker diarization. Although conventional systems only use acoustic features, in some scenarios linguistic data ... -
Linear prediction of the one-sided autocorrelation sequence for noisy speech recognition
(1997-01)
Article
Accés obertThe article presents a robust representation of speech based on AR modeling of the causal part of the autocorrelation sequence. In noisy speech recognition, this new representation achieves better results than several other ... -
Llibre blanc sobre la intel·ligència artificial aplicada a la ciberseguretat
(Centre of Innovation for Data Tech and Artificial Intelligence (CIDAI), 2023)
Llibre
Accés obertEls darrers anys els avanços a la ciència de la Intel·ligència Artificial han estat remarcables, tenint gran impacte en diferents sectors industrials i socials. Existeixen en la actualitat una gran quantitat d’exemples que ... -
Loquax: implementación de un sistema de reconocimiento de locutor en un ordenador personal
(1996)
Text en actes de congrés
Accés obertSistematizar el reconocimiento de locutor, es decir, la capacidad de distinguir el propietario o propietaria de un fragmento de voz humana, es un objetivo perseguido desde los inicios del procesado de la señal y enmarcado ... -
LSTM neural network-based speaker segmentation using acoustic and language modelling
(International Speech Communication Association (ISCA), 2017)
Comunicació de congrés
Accés obertThis paper presents a new speaker change detection system based on Long Short-Term Memory (LSTM) neural networks using acoustic data and linguistic content. Language modelling is combined with two different ... -
Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition
(Institute of Electrical and Electronics Engineers (IEEE), 1997)
Text en actes de congrés
Accés obertSpeech dynamic features are routinely used in current speech recognition systems in combination with short-term (static) spectral features. Although many existing speech recognition systems do not weight both kinds of ... -
Modelado de la señal en reconocimiento de habla ruidosa
(1996)
Text en actes de congrés
Accés obertConventional modelling techniques of speech suffer a very big performance degradation in adverse noisy environments. So, it is necessary to research for more robust representations of speech signal. This paper presents new ... -
Modelado de la trayectoria de los polos en la secuencia de LPC
(Universidad de Valladolid, 1995)
Text en actes de congrés
Accés obertA alternative way of representing time variations of the speech spectra is presented. We propose to model the trajectories of the poles of the LPC analysis spectra using exponential functions as alternative to delta ...
