
Laurent Girin
143
Documents
Publications
Publications
|
AnCoGen: Analysis, Control and Generation of Speech with a Masked AutoencoderICASSP 2025 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2025, Hyderabad, India. pp.1-5
Communication dans un congrès
hal-04891286
v1
|
|
Exploration de la représentation multidimensionnelle de paramètres acoustiques unidimensionnels de la parole extraits par des modèles profonds non supervisés.JEP-TALN-RECITAL 2024 - 35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), Jul 2024, Toulouse, France. pp.82-91
Communication dans un congrès
hal-04623108
v1
|
|
Exploring the Multidimensional Representation of Unidimensional Speech Acoustic Parameters Extracted by Deep Unsupervised ModelsICASSPW 2024 - IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Apr 2024, Seoul (Korea), South Korea. pp.858-862, ⟨10.1109/ICASSPW62465.2024.10669904⟩
Communication dans un congrès
hal-04683650
v1
|
|
Speech Modeling with a Hierarchical Transformer Dynamical VAEICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096751⟩
Communication dans un congrès
hal-04132313
v1
|
Exploring the multidimensional representation of unidimensional speech of acoustic parameters extracted by deep unsupervised modelsJournée commune AFIA-TLH / AFCP – “Extraction de connaissances interprétables pour l’étude de la communication parlée”, AFIA-TLH; AFCP, Dec 2023, Avignon, France
Communication dans un congrès
hal-04416200
v1
|
|
|
Unsupervised speech enhancement with deep dynamical generative speech and noise modelsInterspeech 2023 - 24th Annual Conference of the International Speech Communication Association, ISCA, Aug 2023, Dublin, Ireland. pp.1-5
Communication dans un congrès
hal-04132312
v1
|
|
Exploring the multidimensional representation of individual speech acoustic parameters extracted by deep unsupervised modelsSSW 2023 - 12th ISCA Speech Synthesis Workshop (SSW2023), Aug 2023, Grenoble, France. pp.240-241
Communication dans un congrès
hal-04274170
v1
|
|
Repeat after Me: Self-Supervised Learning of Acoustic-to-Articulatory Mapping by Vocal ImitationICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore. pp.8252-8256, ⟨10.1109/ICASSP43922.2022.9747804⟩
Communication dans un congrès
hal-03688189
v1
|
|
Les auto-encodeurs variationnels dynamiques et leur application à la modélisation de spectrogrammes de paroleJEP 2022 - 34e Journées d’Études sur la Parole, Université de Nantes, Jun 2022, Noirmoutier, France. pp.655-663, ⟨10.21437/JEP.2022-69⟩
Communication dans un congrès
hal-03978396
v1
|
Learning and controlling the source-filter representation of speech with a variational autoencoderCFA 2022 - 16ème Congrès Français d'Acoustique, Société Française d'Acoustique (SFA), Apr 2022, Marseille, France
Communication dans un congrès
hal-03603791
v1
|
|
|
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language modelInterspeech 2022 - 23rd Annual Conference of the International Speech Communication Association, Sep 2022, Incheon, South Korea. pp.3383-3387, ⟨10.21437/Interspeech.2022-10116⟩
Communication dans un congrès
hal-03791472
v1
|
|
Improved feature extraction for CRNN-based multiple sound source localizationEUSIPCO 2021 - 29th European Signal Processing Conference, Aug 2021, Dublin, Ireland. pp.231-235, ⟨10.23919/EUSIPCO54536.2021.9616124⟩
Communication dans un congrès
hal-03537334
v1
|
|
Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text InputInterspeech 2021 - 22nd Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. pp.3865-3869, ⟨10.21437/Interspeech.2021-275⟩
Communication dans un congrès
hal-03372802
v1
|
|
A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram ModelingInterspeech 2021 - 22nd Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. pp.46-50, ⟨10.21437/Interspeech.2021-256⟩
Communication dans un congrès
hal-03295657
v1
|
|
Learning robust speech representation with an articulatory-regularized variational autoencoderInterspeech 2021 - 22nd Annual Conference of the International Speech Communication Association, Aug 2021, Brno, Czech Republic. pp.3345-3349, ⟨10.21437/Interspeech.2021-1604⟩
Communication dans un congrès
hal-03373252
v1
|
|
High-resolution speaker counting in reverberant rooms using CRNN with Ambisonics featuresEUSIPCO 2020 - 28th European Signal Processing Conference, Jan 2021, Amsterdam, Netherlands. pp.71-75, ⟨10.23919/Eusipco47968.2020.9287637⟩
Communication dans un congrès
hal-03537323
v1
|
|
Saladnet: Self-Attentive Multisource Localization in the Ambisonics DomainWASPAA 2021 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2021, New Paltz / Virtual, United States. pp.336-340, ⟨10.1109/WASPAA52581.2021.9632737⟩
Communication dans un congrès
hal-03537340
v1
|
|
Multichannel source counting with CRNN : analysis of the performanceFA 2020 - Forum Acusticum 2020, Dec 2020, Lyon (virtual), France. pp.829-835, ⟨10.48465/fa.2020.0766⟩
Communication dans un congrès
hal-03235360
v1
|
|
Towards an articulatory-driven neural vocoder for speech synthesisISSP 2020 - 12th International Seminar on Speech Production, Dec 2020, Providence (virtual), United States
Communication dans un congrès
hal-03184762
v1
|
|
What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTSInterspeech 2020 - 21st Annual Conference of the International Speech Communication Association, Oct 2020, Shanghai (Virtual Conf), China. pp.215-219, ⟨10.21437/Interspeech.2020-2103⟩
Communication dans un congrès
hal-02962234
v1
|
|
A Recurrent Variational Autoencoder for Speech EnhancementICASSP 2020 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, May 2020, Barcelone (virtual), Spain. pp.371-375, ⟨10.1109/ICASSP40776.2020.9053164⟩
Communication dans un congrès
hal-02329000
v2
|
|
Audio-Visual Variational Fusion for Multi-Person Tracking with RobotsACMMM 2019 - 27th ACM International Conference on Multimedia, Oct 2019, Nice, France. pp.1059-1061, ⟨10.1145/3343031.3350590⟩
Communication dans un congrès
hal-02354514
v1
|
|
Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorizationICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. pp.101-105, ⟨10.1109/ICASSP.2019.8683704⟩
Communication dans un congrès
hal-02005102
v2
|
|
Speech enhancement with variational autoencoders and alpha-stable distributionsICASSP 2019 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom. pp.541-545, ⟨10.1109/ICASSP.2019.8682546⟩
Communication dans un congrès
hal-02005106
v1
|
Autoencoders for music sound modeling : a comparison of linear, shallow, deep, recurrent and variational modelsSMC 2019 - 16th Sound & Music Computing Conference, May 2019, Malaga, Spain
Communication dans un congrès
hal-02349406
v1
|
|
|
Bayesian time-domain multiple sound source localization for a stochastic machineEUSIPCO 2019 - 27th European Signal Processing Conference, Sep 2019, A Coruna, Spain. pp.1-5, ⟨10.23919/EUSIPCO.2019.8902666⟩
Communication dans un congrès
hal-02377220
v1
|
|
Notes on the use of variational autoencoders for speech and audio spectrogram modelingDAFx 2019 - 22nd International Conference on Digital Audio Effects, Sep 2019, Birmingham, United Kingdom. pp.1-8
Communication dans un congrès
hal-02349385
v1
|
|
Online Localization of Multiple Moving Speakers in Reverberant EnvironmentsSAM 2018 - 10th IEEE Workshop on Sensor Array and Multichannel Signal Processing, Jul 2018, Sheffield, United Kingdom. pp.405-409, ⟨10.1109/SAM.2018.8448423⟩
Communication dans un congrès
hal-01795462
v1
|
|
Autonomous Sensorimotor Learning for Sound Source Localization by a Humanoid RobotIROS 2018 - Workshop on Crossmodal Learning for Intelligent Robotics in conjunction with IEEE/RSJ IROS, Oct 2018, Madrid, Spain
Communication dans un congrès
hal-01921882
v1
|
|
Accounting for Room Acoustics in Audio-Visual Multi-Speaker TrackingICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada. pp.6553-6557, ⟨10.1109/ICASSP.2018.8462100⟩
Communication dans un congrès
hal-01718114
v1
|
|
Exploiting the Complementarity of Audio and Visual Data in Multi-Speaker TrackingICCVW 2017 - IEEE International Conference on Computer Vision Workshops, Oct 2017, Venise, Italy. pp.446-454, ⟨10.1109/ICCVW.2017.60⟩
Communication dans un congrès
hal-01577965
v1
|
|
A variance modeling framework based on variational autoencoders for speech enhancementMLSP 2018 - IEEE 28th International Workshop on Machine Learning for Signal Processing, Sep 2018, Aalborg, Denmark. pp.1-6, ⟨10.1109/MLSP.2018.8516711⟩
Communication dans un congrès
hal-01832826
v1
|
|
Multisource MINT Using the Convolutive Transfer FunctionICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada. pp.756-760, ⟨10.1109/ICASSP.2018.8462607⟩
Communication dans un congrès
hal-01718106
v1
|
|
A Cascaded Multiple-Speaker Localization and Tracking SystemIWAENC - LOCATA Challenge Workshop - a satellite event of IWAENC 2018, Sep 2018, Tokyo, Japan. pp.1-5
Communication dans un congrès
hal-01957137
v1
|
|
Audio Source Separation Based on Convolutive Transfer Function and Frequency-Domain Lasso OptimizationICASSP 2017 - IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2017, New Orleans, United States. pp.541-545, ⟨10.1109/ICASSP.2017.7952214⟩
Communication dans un congrès
hal-01430754
v1
|
|
Exploiting the Intermittency of Speech for Joint Separation and DiarizationWASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, NY, United States. pp.41-45, ⟨10.1109/WASPAA.2017.8169991⟩
Communication dans un congrès
hal-01568813
v1
|
|
Adaptation of a Gaussian Mixture Regressor to a New Input Distribution: Extending the C-GMR FrameworkLVA/ICA 2017 - 13th International Conference on Latent Variable Analysis and Signal Separation, Feb 2017, Grenoble, France. pp.459-468, ⟨10.1007/978-3-319-53547-0_43⟩
Communication dans un congrès
hal-01646098
v1
|
|
An EM Algorithm for Audio Source Separation Based on the Convolutive Transfer FunctionWASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, NY, United States. pp.56-60, ⟨10.1109/WASPAA.2017.8169994⟩
Communication dans un congrès
hal-01568818
v1
|
|
An EM Algorithm for Joint Source Separation and Diarisation of Multichannel Convolutive Speech MixturesICASSP 2017 - IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2017, New Orleans, United States. pp.16-20, ⟨10.1109/ICASSP.2017.7951789⟩
Communication dans un congrès
hal-01430761
v1
|
|
On the Use of Latent Mixing Filters in Audio Source SeparationLVA/ICA 2017 - 13th International Conference on Latent Variable Analysis and Signal Separation, Feb 2017, Grenoble, France. pp.225-235, ⟨10.1007/978-3-319-53547-0_22⟩
Communication dans un congrès
hal-01400965
v1
|
|
Explaining the Parameterized Wiener Filter with Alpha-Stable ProcessesWASPAA 2017 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, Oct 2017, New Paltz, New York, United States
Communication dans un congrès
hal-01548508
v1
|
|
A Bayesian stochastic machine for sound source localizationICRC 2017 - IEEE International Conference on Rebooting Computing, Nov 2017, Washington, DC, United States. pp.1-8
Communication dans un congrès
hal-01644346
v1
|
|
Non-Stationary Noise Power Spectral Density Estimation Based on Regional StatisticsICASSP 2016 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE Signal Processing Society, Mar 2016, Shanghai, China. pp.181-185, ⟨10.1109/ICASSP.2016.7471661⟩
Communication dans un congrès
hal-01250892
v1
|
|
Voice Activity Detection Based on Statistical Likelihood Ratio With Adaptive ThresholdingIWAENC 2016 - International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2016, Xi'an, China. pp.1-5, ⟨10.1109/IWAENC.2016.7602911⟩
Communication dans un congrès
hal-01349776
v1
|
|
Reverberant Sound Localization with a Robot Head Based on Direct-Path Relative Transfer FunctionIEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Oct 2016, Daejeon, South Korea. pp.2819-2826, ⟨10.1109/IROS.2016.7759437⟩
Communication dans un congrès
hal-01349771
v1
|
|
An Inverse-Gamma Source Variance Prior with Factorized Parameterization for Audio Source SeparationICASSP 2016 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE Signal Processing Society, Mar 2016, Shanghai, China. pp.136-140, ⟨10.1109/ICASSP.2016.7471652⟩
Communication dans un congrès
hal-01253169
v1
|
Deep neural networks for automatic detection of screams and shouted speech in subway trainsICASSP 2016 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2016, Shanghai, China. pp.6460-6464, ⟨10.1109/ICASSP.2016.7472921⟩
Communication dans un congrès
hal-01385272
v1
|
|
|
Local Relative Transfer Function for Sound Source LocalizationEUSIPCO 2015 - 23th European Signal Processing Conference, Aug 2015, Nice, France. pp.399-403, ⟨10.1109/EUSIPCO.2015.7362413⟩
Communication dans un congrès
hal-01163675
v1
|
|
Estimation of Relative Transfer Function in the Presence of Stationary Noise Based on Segmental Power Spectral Density Matrix SubtractionICASSP 2015 - 40th IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2015, Brisbane, Australia. pp.320 - 324, ⟨10.1109/ICASSP.2015.7177983⟩
Communication dans un congrès
hal-01119186
v1
|
|
A Variational EM Algorithm for the Separation of Moving Sound SourcesWASPAA 2015 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, IEEE Signal Processing Society, Oct 2015, New Paltz, NY, United States. pp.1-5, ⟨10.1109/WASPAA.2015.7336936⟩
Communication dans un congrès
hal-01169764
v2
|
|
Real-time Control of a DNN-based Articulatory Synthesizer for Silent Speech Conversion: a pilot studyInterspeech 2015 - 16th Annual Conference of the International Speech Communication Association, Sep 2015, Dresden, Germany
Communication dans un congrès
hal-01726265
v1
|
|
Sound Representation and Classification Benchmark for Domestic RobotsICRA 2014 - IEEE International Conference on Robotics and Automation, May 2014, Hong Kong, China. pp.6285-6292, ⟨10.1109/ICRA.2014.6907786⟩
Communication dans un congrès
hal-00952092
v1
|
|
Robust Articulatory Speech Synthesis using Deep Neural Networks for BCI ApplicationsInterspeech 2014 - 15th Annual Conference of the International Speech Communication Association, Sep 2014, Singapour, Singapore
Communication dans un congrès
hal-01228891
v1
|
|
Mapping Sounds on Images Using Binaural SpectrogramsEUSIPCO 2014 - 22th European Signal Processing Conference, Sep 2014, Lisbonne, Portugal. pp.2470 - 2474
Communication dans un congrès
hal-01019287
v1
|
|
Perceptual coding-based informed source separationEUSIPCO 2014 - 22th European Signal Processing Conference, Sep 2014, Lisbonne, Portugal
Communication dans un congrès
hal-01016314
v1
|
|
Supervised Classification of Baboon VocalizationsNIPS4B - Workshop: Neural Information Processing Scaled for Bioacoustics : NIPS4B, Dec 2013, Lake Tahoe, NV/CA, United States. 10 p
Communication dans un congrès
hal-00910104
v1
|
|
Informed Source Separation from compressed mixtures using spatial wiener filter and quantization noise estimationICASSP 2013 - 38th IEEE International Conference on Acoustics, Speech and Signal Processing, May 2013, Vancouver, Canada. pp.61-65, ⟨10.1109/ICASSP.2013.6637609⟩
Communication dans un congrès
hal-00940328
v1
|
|
A Simple Hybrid Acoustic / Morphologically Constrained Technique for the Synthesis of Stop Consonants in Various Vocalic ContextsInterspeech 2012 - 13th Annual Conference of the International Speech Communication Association, Sep 2012, Portland, United States. pp.Thu.P10a.05
Communication dans un congrès
hal-00807519
v1
|
|
Sound-Event Recognition with a Companion HumanoidHumanoids 2012 - IEEE International Conference on Humanoid Robotics, Nov 2012, Osaka, Japan. pp.104-111, ⟨10.1109/HUMANOIDS.2012.6651506⟩
Communication dans un congrès
hal-00768767
v1
|
|
DReaM: A Novel System for Joint Source Separation and Multi-Track CodingAES 2012 - 133rd AES Convention, Oct 2012, San Francisco, United States. CD 133papers
Communication dans un congrès
hal-00809503
v1
|
|
Phase-based informed source separation for active listening of musicDAFx 2012 - 15th International Conference on Digital Audio Effects, Sep 2012, York, United Kingdom. pp.n/c
Communication dans un congrès
hal-00807001
v1
|
|
Linear Mixing Models for Active Listening of Music Productions in Realistic Studio ConditionsAES 2012 - 132nd AES Convention, Apr 2012, Budapest, Hungary. Paper 8594
Communication dans un congrès
hal-00790783
v1
|
|
Professionally-produced music separation guided by coversISMIR 2012 - International Society for Music Information Retrieval Conference, Oct 2012, Porto, Portugal. pp.n/c
Communication dans un congrès
hal-00807027
v1
|
|
Informed Audio Source Separation: A Comparative StudyEUSIPCO 2012 - 20th European Signal Processing Conference, Aug 2012, Bucarest, Romania. pp.n/c
Communication dans un congrès
hal-00809525
v1
|
|
Informed audio source separation from compressed linear stereo mixturesAES 2011 - 42nd International Conference: Semantic Audio, Jul 2011, Ilmenau, Germany. pp.159-168
Communication dans un congrès
hal-00695724
v1
|
|
A high-rate data hiding technique for audio signals based on IntMDCT quantizationDAFx 2011 - 14th International Conference on Digital Audio Effects, Sep 2011, Paris, France. pp.353-356
Communication dans un congrès
hal-00695759
v1
|
|
Sparsification" of audio signals using the MDCT/IntMDCT and a psychoacoustic model - Application to informed audio source separationAES 2011 - 42nd International Conference: Semantic Audio, Jul 2011, Ilmenau, Germany. pp.179-188
Communication dans un congrès
hal-00695730
v1
|
|
An informed source separation system for speech signalsInterspeech 2011 - 12th Annual Conference of the International Speech Communication Association, Aug 2011, Florence, Italy. pp.573-576
Communication dans un congrès
hal-00695758
v1
|
|
A long-term harmonic plus noise model for speech signalsInterspeech 2011 - 12th Annual Conference of the International Speech Communication Association, Aug 2011, Florence, Italy. pp.53-56
Communication dans un congrès
hal-00695752
v1
|
Hybrid coding/indexing strategy for informed source separation of linear instantaneous under-determined audio mixturesICA 2010 - 20th International Congress on Acoustics, Aug 2010, Sydney, Australia. pp.ICA2010
Communication dans un congrès
hal-00535684
v1
|
|
Long-term modelling of parameters trajectories for the harmonic plus noise model of speech signalsICA 2010 - 20th International Congress on Acoustics, Aug 2010, Sydney, Australia. pp.ICA2010
Communication dans un congrès
hal-00534497
v1
|
|
|
Une technique de tatouage " haute-capacité " pour signaux musicaux au format CD-audioCFA 2010 - 10ème Congrès Français d'Acoustique, Apr 2010, Lyon, France
Communication dans un congrès
hal-00542884
v1
|
|
Séparation de source informée pour des mélanges stéréo instantanés utilisant un tatouage de l'index des sources localement prédominantesCFA 2010 - 10ème Congrès Français d'Acoustique, Apr 2010, Lyon, France. pp.Cd-Rom
Communication dans un congrès
hal-00486818
v1
|
|
Interactive Music with Active Audio CDsCMMR 2010 - 7th International Symposium on Computer Music Modeling and Retrieval, Jun 2010, Málaga, Spain. pp.73--74
Communication dans un congrès
hal-00502792
v1
|
Linking Motion Sensors and Digital Signal Processing for Real-Time Musical TransformationsHAID 2010 - 5th International Workshop Haptic Audio Interaction Design, Sep 2010, Copenhague, Denmark. pp.HAID2010
Communication dans un congrès
hal-00535694
v1
|
|
A high-capacity watermarking technique for audio signals based on MDCT-domain quantizationICA 2010 - 20th International Congress on Acoustics, Aug 2010, Sydney, Australia. pp.ICA2010
Communication dans un congrès
hal-00534502
v1
|
|
|
Informed source separation of underdetermined instantaneous stereo mixtures using source index embeddingICASSP 2010 - IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2010, Dallas, United States. pp.245-248
Communication dans un congrès
hal-00486804
v1
|
A watermarking-based method for single-channel audio source separationICASSP 2009 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2009, Taipei, Taiwan. pp.1
Communication dans un congrès
hal-00361713
v1
|
|
Estimation of the Voicing Cut-Off Frequency Contour of Natural Speech Based on Harmonic and Aperiodic EnergiesICASSP 2008 - IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2008, Las Vegas, Nevada, United States
Communication dans un congrès
hal-00329764
v1
|
|
Long-Term Flexible 2D Cepstral Modeling of Speech Spectral AmplitudesICASSP 2008 - IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2008, Las Vegas, Nevada, United States
Communication dans un congrès
hal-00329752
v1
|
|
|
Using a Visual Voice Activity Detector to Regularize the Permutations in Blind Separation of Convolutive Speech MixturesDSP 2007 - 15th IEEE International Conference on Digital Signal Processing, Jul 2007, Cardiff, United Kingdom. pp.223-226, ⟨10.1109/ICDSP.2007.4288559⟩
Communication dans un congrès
hal-00173341
v1
|
Development and comparison of two approaches for visual speech analysis with application to voice activity detectionAVSP 2007 - 6th International Conference on Auditory-Visual Speech Processing, Aug 2007, Hilvarenbeek, Netherlands. p. 228-232
Communication dans un congrès
hal-00195015
v1
|
|
Long-term quantization of speech LSF parametersICASSP 2007 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2007, Honolulu, Hawaii, United States. pp.845
Communication dans un congrès
hal-00194157
v1
|
|
Audiovisual speech source separation: a regularization method based on visual voice activity detectionAVSP 2007 - 6th International Conference on Auditory-Visual Speech Processing, Aug 2007, Hilvarenbeek, Netherlands. pp.223-227
Communication dans un congrès
hal-00195014
v1
|
|
|
Two novel visual voice activity detectors based on appearance models and retinal fillteringEUSIPCO 2007 - 15th European Signal Processing Conference, Sep 2007, Poznan, Poland
Communication dans un congrès
hal-00188132
v1
|
Theoretical and experimental bases of a new method for accurate separation of harmonic and noise components of speech signalsEuropean Signal Processing conference (EUSIPCO), Sep 2006, Florence, Italy. pp.1
Communication dans un congrès
hal-00372280
v1
|
|
|
ARTUS : calcul et tatouage audiovisuel des mouvements d'un personnage animé virtuel pour l'accessibilité d'émissions télévisuelles aux téléspectateurs sourds comprenant la Langue Française Parlée ComplétéeHandicap, Jun 2006, Paris, France. pp.265-270
Communication dans un congrès
hal-00366492
v1
|
Solving the indeterminations of Blind source separation of convolutive speech mixturesIEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2006, 2006, Toulouse, France
Communication dans un congrès
hal-00098153
v1
|
|
An analysis of visual speech information applied to voice activity detectionIEEE International Conference on Acoustics, Speech, and Signal Processing, May 2006, Toulouse, France. pp.1
Communication dans un congrès
hal-00361750
v1
|
|
Comparing Several Models for Perceptual Long-Term Modeling of Amplitudes and Phase Trajectories of Sinusoidal SpeechProceedings of the INTERSPEECH -- EUROSPEECH Conference, Sep 2005, Portugal. pp.357-360
Communication dans un congrès
hal-00308299
v1
|
|
|
A Generalized Polynomial And Sinusoidal Model For Partial Tracking And Time StretchingProceedings of the Digital Audio Effects (DAFx05) Conference, Sep 2005, Spain. pp.24--29
Communication dans un congrès
hal-00307987
v1
|
Long Term Modeling of Phase Trajectories within the Speech Sinusoidal Model FrameworkINTERSPEECH - 8th International Conference on Spoken Language Processing (ICSLP04), Oct 2004, South Korea. pp.2469-2472
Communication dans un congrès
hal-00308298
v1
|
|
Watermarking of Speech Signals Using the Sinusoidal Model and Frequency Modulation of the PartialsIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2004, Canada. pp.I - 633-6
Communication dans un congrès
hal-00308297
v1
|
|
|
Characterizing and classifying Cued Speech vowels from labial parameters8th International Conference on Spoken Language Processing (ICSLP'04 or InterSpeech'04), 2004, Jeju, South Korea
Communication dans un congrès
hal-00328134
v1
|
Comparing the Order of a Polynomial Phase Model for the Synthesis of Quasi-Harmonic Audio SignalsIEEE Workshop on Applications of Signal Processing to Audio and Acoustics - WASPAA'03, Oct 2003, New York, United States. pp.193- 196
Communication dans un congrès
hal-00308296
v1
|
|
Dynamical Variational Autoencoders: A Comprehensive Review, 15 (1-2), pp.197, 2021, Foundations and Trends® in Machine Learning, 978-1-68083-913-5. ⟨10.1561/2200000089⟩
Ouvrages
hal-02926215
v2
|
|
Audio source separation into the wildMultimodal Behavior Analysis in the Wild, Academic Press (Elsevier), pp.53-78, 2018, Computer Vision and Pattern Recognition, ⟨10.1016/B978-0-12-814601-9.00022-5⟩
Chapitre d'ouvrage
hal-01943375
v1
|
Procédé de traitement numérique sur un ensemble de pistes audio avant mixageFrance, N° de brevet: FR 2984579. 2013, pp.20
Brevet
hal-01021287
v1
|
|
Procédé et dispositif de formation d'un signal mixé, procédé et dispositif de séparation de signaux, et signal correspondantFrance, N° de brevet: FR 2944403. 2010, pp.20
Brevet
hal-01021265
v1
|
|
Method and device for forming a digital audio mixed signal, method and device for separating signals, and corresponding signalFrance, Patent n° : US20140037110A1. 2010
Brevet
hal-02651076
v1
|
|
Fill in the Gap! Combining Self-supervised Representation Learning with Neural Audio Synthesis for Speech Inpainting2024
Pré-publication, Document de travail
hal-04728251
v1
|
Chargement...
Chargement...