Presentation is loading. Please wait.

Presentation is loading. Please wait.

Page 1 NOLISP, Paris, May 23rd 2007 Audio-Visual Audio-Visual Subspaces Audio Visual Reduced Audiovisual Subspace Principal Component & Linear Discriminant.

Published byAnnis Fields Modified over 8 years ago

Similar presentations

Presentation on theme: "Page 1 NOLISP, Paris, May 23rd 2007 Audio-Visual Audio-Visual Subspaces Audio Visual Reduced Audiovisual Subspace Principal Component & Linear Discriminant."— Presentation transcript:

1 Page 1 NOLISP, Paris, May 23rd 2007 Audio-Visual Audio-Visual Subspaces Audio Visual Reduced Audiovisual Subspace Principal Component & Linear Discriminant Analysis x Correlated Audio & Visual Subspaces Co-inertia & Canonical Correlation Analysis

2 Page 2 NOLISP, Paris, May 23rd 2007 Voice conversion techniques Definition: Process of making one person’s voice « source » sounds like another person’s voice target source target Voice conversion My name is John

3 Page 3 NOLISP, Paris, May 23rd 2007 Principle of ALISP Dictionary of representative segments Spectral analysis Prosodic analysis Selection of segmental units Segment index Prosodic parameters Input speech Concatenative synthesis HNM Output speech CODER

4 Page 4 NOLISP, Paris, May 23rd 2007 details of Encoding speech Spectral analysis Prosodic analysis HMM Recognition Dictionary of HMM models of ALISP classes Synth unit A 1 … Synth unit A 8 HMM A Representative units of the class Selection by DTW Prosodic encoding Index of ALISP class Index of synth. unit Pitch, energy, duration

5 Page 5 NOLISP, Paris, May 23rd 2007 Details of decoding Output speech Synth unit A 1 … Synth unit A 8 ALISP Index Synth unit index within class Prosodic parameters Loading Synth unit Concatenative synthesis

6 Page 6 NOLISP, Paris, May 23rd 2007 Principle of Alisp conversion Learning step: one hour of target voice - Parametric analysis: MFCC - Segmentation based on temporal decompostion and vector quantization - Stochastic modelling based on HMM - Creation of representative units Conversion step - Parametric analysis: MFCC - HMM recognition - Selection of representative segment  DTW Synthesis step - Concatenation of representative - HNM synthesis

7 Page 7 NOLISP, Paris, May 23rd 2007 Voice conversion using ALISP results Score distributionDET curve EER before forgery: 16 % (1729 impostors, 1320 clients) EER after forgery : 26 % (1729 impostors, 1320 clients)

8 Page 8 NOLISP, Paris, May 23rd 2007 Voice conversion using ALISP results BREF databaseNIST database Source Result Target SourceTarget Result female male

Download ppt "Page 1 NOLISP, Paris, May 23rd 2007 Audio-Visual Audio-Visual Subspaces Audio Visual Reduced Audiovisual Subspace Principal Component & Linear Discriminant."

Similar presentations

PF-STAR: emotional speech synthesis Istituto di Scienze e Tecnologie della Cognizione, Sezione di Padova – “Fonetica e Dialettologia”, CNR.

PF-STAR: emotional speech synthesis Istituto di Scienze e Tecnologie della Cognizione, Sezione di Padova – “Fonetica e Dialettologia”, CNR.
Improved ASR in noise using harmonic decomposition Introduction Pitch-Scaled Harmonic Filter Recognition Experiments Results Conclusion aperiodic contribution.

Improved ASR in noise using harmonic decomposition Introduction Pitch-Scaled Harmonic Filter Recognition Experiments Results Conclusion aperiodic contribution.
Robust Speech recognition V. Barreaud LORIA. Mismatch Between Training and Testing n mismatch influences scores n causes of mismatch u Speech Variation.

Robust Speech recognition V. Barreaud LORIA. Mismatch Between Training and Testing n mismatch influences scores n causes of mismatch u Speech Variation.
1 Analysis of Parameter Importance in Speaker Identity Ricardo de Córdoba, Juana M. Gutiérrez-Arriola Speech Technology Group Departamento de Ingeniería.

1 Analysis of Parameter Importance in Speaker Identity Ricardo de Córdoba, Juana M. Gutiérrez-Arriola Speech Technology Group Departamento de Ingeniería.
Audio Visual Speech Recognition

Audio Visual Speech Recognition
STQ Workshop, Sophia-Antipolis, February 11 th, 2003 Packet loss concealment using audio morphing Franck Bouteille¹ Pascal Scalart² Balazs Kövesi² ¹ PRESCOM.

STQ Workshop, Sophia-Antipolis, February 11 th, 2003 Packet loss concealment using audio morphing Franck Bouteille¹ Pascal Scalart² Balazs Kövesi² ¹ PRESCOM.
Voiceprint System Development Design, implement, test unique voiceprint biometric system Research Day Presentation, May 3 rd 2013 Rahul Raj (Team Lead),

Voiceprint System Development Design, implement, test unique voiceprint biometric system Research Day Presentation, May 3 rd 2013 Rahul Raj (Team Lead),
Speech & Audio Coding TSBK01 Image Coding and Data Compression Lecture 11, 2003 Jörgen Ahlberg.

Speech & Audio Coding TSBK01 Image Coding and Data Compression Lecture 11, 2003 Jörgen Ahlberg.
Tangent Vectors and Normal Vectors. Definitions of Unit Tangent Vector.

Tangent Vectors and Normal Vectors. Definitions of Unit Tangent Vector.
High Level Prosody features: through the construction of a model for emotional speech Loic Kessous Tel Aviv University Speech, Language and Hearing

High Level Prosody features: through the construction of a model for emotional speech Loic Kessous Tel Aviv University Speech, Language and Hearing
Prosody modification in speech signals Project by Edi Fridman & Alex Zalts supervision by Yizhar Lavner.

Prosody modification in speech signals Project by Edi Fridman & Alex Zalts supervision by Yizhar Lavner.
Pitch Prediction From MFCC Vectors for Speech Reconstruction Xu shao and Ben Milner School of Computing Sciences, University of East Anglia, UK Presented.

Pitch Prediction From MFCC Vectors for Speech Reconstruction Xu shao and Ben Milner School of Computing Sciences, University of East Anglia, UK Presented.
Abstract This article investigates the importance of the vocal source information for speaker recogni- tion. We propose a novel feature extraction scheme.

Abstract This article investigates the importance of the vocal source information for speaker recogni- tion. We propose a novel feature extraction scheme.
Speaker Recognition Sharat.S.Chikkerur Center for Unified Biometrics and Sensors

Speaker Recognition Sharat.S.Chikkerur Center for Unified Biometrics and Sensors
Speech in Multimedia Hao Jiang Computer Science Department Boston College Oct. 9, 2007.

Speech in Multimedia Hao Jiang Computer Science Department Boston College Oct. 9, 2007.
VOICE CONVERSION METHODS FOR VOCAL TRACT AND PITCH CONTOUR MODIFICATION Oytun Türk Levent M. Arslan R&D Dept., SESTEK Inc., and EE Eng. Dept., Boğaziçi.

VOICE CONVERSION METHODS FOR VOCAL TRACT AND PITCH CONTOUR MODIFICATION Oytun Türk Levent M. Arslan R&D Dept., SESTEK Inc., and EE Eng. Dept., Boğaziçi.
Emotions and Voice Quality: Experiments with Sinusoidal Modeling Authors: Carlo Drioli, Graziano Tisato, Piero Cosi, Fabio Tesser Institute of Cognitive.

Emotions and Voice Quality: Experiments with Sinusoidal Modeling Authors: Carlo Drioli, Graziano Tisato, Piero Cosi, Fabio Tesser Institute of Cognitive.
Robust Voice Activity Detection for Interview Speech in NIST Speaker Recognition Evaluation Man-Wai MAK and Hon-Bill YU The Hong Kong Polytechnic University.

Robust Voice Activity Detection for Interview Speech in NIST Speaker Recognition Evaluation Man-Wai MAK and Hon-Bill YU The Hong Kong Polytechnic University.
SecurePhone Workshop - 24/25 June 2004 1 Speaking Faces Verification Kevin McTait Raphaël Blouet Gérard Chollet Silvia Colón Guido Aversano.

SecurePhone Workshop - 24/25 June Speaking Faces Verification Kevin McTait Raphaël Blouet Gérard Chollet Silvia Colón Guido Aversano.
1 Cours parole du 9 Mars 2005 enseignants: Dr. Dijana Petrovska-Delacrétaz et Gérard Chollet Reconnaissance du locuteur 1.Introduction, Historique, Domaines.

1 Cours parole du 9 Mars 2005 enseignants: Dr. Dijana Petrovska-Delacrétaz et Gérard Chollet Reconnaissance du locuteur 1.Introduction, Historique, Domaines.

Similar presentations

Ads by Google