Filters








3,546 Hits in 4.7 sec

EEG decoding of spoken words in bilingual listeners: from words to language invariant semantic-conceptual representations

João M. Correia, Bernadette Jansma, Lars Hausfeld, Sanne Kikkert, Milene Bonte
2015 Frontiers in Psychology  
Furthermore, employing two EEG feature selection approaches, we assessed the contribution of temporal and oscillatory EEG features to our classification results.  ...  Both types of classification, showed a strong contribution of oscillations below 12 Hz, indicating the importance of low frequency oscillations in the neural representation of individual words and concepts  ...  specific frequency bands occurred in time windows relevant for word decoding ( Figure 4C) .  ... 
doi:10.3389/fpsyg.2015.00071 pmid:25705197 pmcid:PMC4319403 fatcat:dthnyajhqfbtdk2rgkunv3o3vu

An Automatic Speaker Recognition System For Intelligence Applications

Federico Avanzini, Federico Flego, Enrico Marchetto
2009 Zenodo  
Publication in the conference proceedings of EUSIPCO, Glasgow, Scotland, 2009  ...  Short-time spectral information of a speaker's voice is extracted in the form of a time-series of feature vectors, usually composed of Mel-Frequency Cepstral Coefficients (MFCCs).  ...  In a listening session, the operator is prompted with a list of available recordings, labeled with date, time, duration and other relevant information (e.g. incoming/outgoing phone numbers in case of phone  ... 
doi:10.5281/zenodo.41687 fatcat:xajd57df6fgcrguhdwkat3ogv4

Analysis of Different Feature for Language Identification

Snehal V., J. V.
2016 International Journal of Computer Applications  
For the relevant languages under the different acoustic condition are used to capture robust feature extraction scheme.  ...  MFCC, GFCC, PLP and the combination of these feature are consider in language identification system.  ...  FUTURE SCOPE Implementation of this technique consider number of features and classification methods for language identification.  ... 
doi:10.5120/ijca2016910924 fatcat:nmdwxj2fjnhv5lhld3sjccbuia

MFCC and Prosodic Feature Extraction Techniques: A Comparative Study

Nilu Singh, R. A. Khan, Raj Shree
2012 International Journal of Computer Applications  
In this paper, we explore the usefulness of prosodic features for syllable classification and MFCC for feature extraction of a speech signal followed by comparison between them.  ...  Here we try to cover-up most of the comparative features of Mel Frequency Cepstral Coefficient and prosodic features.  ...  The MFCC contain both time and frequency information of the signal and this makes them more useful for feature extraction.  ... 
doi:10.5120/8529-2061 fatcat:lhumv7qkofatzj3v3udvecocke

Within-Speaker Features for Native Language Recognition in the Interspeech 2016 Computational Paralinguistics Challenge

Mark Huckvale
2016 Interspeech 2016  
Instead, the objectives of this study were to explore whether within-speaker features found to be effective in ACCDIST would also have value within a contemporary GMM-based accent recognition approach.  ...  The Interspeech 2016 Native Language recognition challenge was to identify the first language of 867 speakers from their spoken English.  ...  Acknowledgements Thanks to the organisers of the Interspeech 2016 Computational Paralinguistics Challenge for making this study possible. 7.  ... 
doi:10.21437/interspeech.2016-1466 dblp:conf/interspeech/Huckvale16 fatcat:xwuaeu5ifncvho2hpislodl63u

Applying multiple classifiers and non-linear dynamics features for detecting sleepiness from speech

Jarek Krajewski, Sebastian Schnieder, David Sommer, Anton Batliner, Björn Schuller
2012 Neurocomputing  
The best models for the phonetic feature set achieved 78.3% (NaïveBayes) for male and 68.5% (Bagging Bayes Net) for female speaker classification accuracy in detecting sleepiness.  ...  Several NLD and phonetic features show significant correlations to KSS ratings, e.g., from the NLD features for male speakers the skewness of vector length within reconstructed phase space (r = .56), and  ...  The phonetic feature set achieved a UA of 78.3% (NaïveBayes) for male and of 68.5% for female speakers (Bagging Bayes Net).  ... 
doi:10.1016/j.neucom.2011.12.021 fatcat:ze3qqjfbifdjldzxy4vlvccsou

Selective Fusion for Speaker Verification in Surveillance [chapter]

Yosef A. Solewicz, Moshe Koppel
2005 Lecture Notes in Computer Science  
While some existing systems fuse several classifier outputs, the proposed method uses a selective fusion scheme that takes into account conveying channel, speaking style and speaker stress as estimated  ...  This paper presents an improved speaker verification technique that is especially appropriate for surveillance scenarios.  ...  After some preliminary calibration, RBF was the chosen kernel for all SVMs with a radius of 10 for the phonetic and prosodic feature sets and a radius of 100 for the idiolectal feature set.  ... 
doi:10.1007/11427995_22 fatcat:d53c6d662ngx3mufaf3wl2i7bi

HMM-based speech recognition using state-dependent, discriminatively derived transforms on mel-warped DFT features

R. Chengalvarayan, Li Deng
1997 IEEE Transactions on Speech and Audio Processing  
The proposed model focuses on dimensionality reduction of the mel-warped discrete fourier transform (DFT) feature space subject to maximal preservation of speech classification information, and aims at  ...  In the study reported in this paper, we investigate interactions of front-end feature extraction and back-end classification techniques in hidden Markov model-based (HMMbased) speech recognition.  ...  Lee for valuable discussions on the MCE approach, and they would like to thank the reviewers and the associate editor who provided valuable suggestions improving the quality of the paper.  ... 
doi:10.1109/89.568731 fatcat:4cowprktefbypjfl3spwhqwzdi

Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features

Maria Markaki, Yannis Stylianou
2011 Speech Communication  
In order to address the varying degrees of redundancy and discriminative power of the acoustic and modulation frequency subspaces, we first employ a generalization of SVD to tensors (Higher Order SVD)  ...  In audio content analysis, the discrimination of speech and non-speech is the first processing step before speaker segmentation and recognition, or speech transcription.  ...  The suggested features span a segment of 500 ms which is roughly equivalent to two syllables duration; hence, they can capture sound patterns present in a language and that's how they complement MFCC features  ... 
doi:10.1016/j.specom.2010.08.007 fatcat:asmedrqgdjcu5d37bgvtsjzc74

CNN with Phonetic Attention for Text-Independent Speaker Verification

Tianyan Zhou, Yong Zhao, Jinyu Li, Yifan Gong, Jian Wu
2019 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)  
In implicit phonetic attention (IPA), the phonetic features are projected by a transformation network into multi-channel feature maps, and then concatenated with the raw acoustic features as the input  ...  With the incorporation of spoken content and attention mechanism, the system can not only distill the speaker-discriminant frames but also actively normalize the phonetic variations.  ...  For voiced area, the weights of different heads exhibits different patterns. The relevance between the weights and phonetic context demands further study.  ... 
doi:10.1109/asru46091.2019.9003826 dblp:conf/asru/ZhouZLGW19 fatcat:a7wfr4mcgbad7ayils23aajidy

A Review on Speech Recognition Technique

Santosh K. Gaikwad, Bharti W. Gawali, Pravin Yannawar
2010 International Journal of Computer Applications  
This paper is concludes with the decision on feature direction for developing technique in human computer interface system using Marathi Language.  ...  and also gives overview technique developed in each stage of speech recognition.  ...  The authors would like to thank the university authorities for Providing infrastructure to carry out the experiments. This work is supported by DST.  ... 
doi:10.5120/1462-1976 fatcat:zx4z3uczqjh2hhnrtc46b3rycu

Page 799 of Behavior Research Methods Vol. 41, Issue 3 [page]

2009 Behavior Research Methods  
Furthermore, these 174 speech feature contours are modeled in average by 129.56 func¬ tionals in time and frequency domain feature space. 1.  ...  (e.g., spectral energy of low-frequency bands vs. high-frequency bands), and state space features (e.g., largest Lyapunov coefficient); auto¬ matic feature generation (genetic algorithms).  ... 

Time-Scale Feature Extractions for Emotional Speech Characterization

Mohamed Chetouani, Ammar Mahdhaoui, Fabien Ringeval
2009 Cognitive Computation  
A timescale based on both vowels and consonants is proposed and it provides a relevant and discriminant feature space for acted emotion recognition.  ...  This article discusses the time-scale analysis problem in feature extraction for emotional speech processing.  ...  Section ''Data-Driven Approach for Time-Scale Feature Extraction'' highlights the relevance of the pseudo-phonetic strategy for emotion recognition and provides results and discussion for time-scale analysis  ... 
doi:10.1007/s12559-009-9016-9 fatcat:gxmttfmq7rb4bdehpg5la5suni

Back-and-Forth Methodology for Objective Voice Quality Assessment: From/to Expert Knowledge to/from Automatic Classification of Dysphonia

Corinne Fredouille, Gilles Pouchoulin, Alain Ghio, Joana Revis, Jean-François Bonastre, Antoine Giovanni
2009 EURASIP Journal on Advances in Signal Processing  
Firstly, focused on the frequency domain, the classification system showed the interest of 0-3000 Hz frequency band for the classification task based on the GRBAS scale.  ...  Later, an automatic phonemic analysis underlined the significance of consonants and more surprisingly of unvoiced consonants for the same classification task.  ...  very relevant for the classification task.  ... 
doi:10.1155/2009/982102 fatcat:7oj3fx5mm5eoflgeqndl4otgpi

A Phonetic Corpus of Spanish Male Twins and Siblings: Corpus Design and Forensic Application

Eugenia San Segundo Fernández
2013 Procedia - Social and Behavioral Sciences  
and 12 non-twin reference-population speakers.  ...  Within a forensic-phonetic approach, the study of twins' voices is particularly relevant, as these (especially monozygotic twins) represent the most extreme physical similarity in human beings.  ...  and also thanks to a grant awarded by the IAFPA (International Association for Forensic Phonetics and Acoustics).  ... 
doi:10.1016/j.sbspro.2013.10.622 fatcat:plswz3s5ufgd7n2fkxunxyfk3a
« Previous Showing results 1 — 15 out of 3,546 results