DIFFERENTIABLE POOLING FOR UNSUPERVISED SPEAKER ADAPTATION Pawel Swietojanski and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB {p.swietojanski, s.renals}@ed.ac.uk ABSTRA

Source URL: www.cstr.inf.ed.ac.uk

• Automatic identification and data capture
• Artificial neural networks
• Computational neuroscience
• Machine learning
• Computer accessibility
• Speech recognition
• Convolutional neural network
• Speaker recognition
• Neocognitron
• Unsupervised learning
• FMLLR
• Pattern recognition

Copyright 2013 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a

Source URL: www.wjscheirer.com

• Biometrics
• Security
• Computer access control
• Identification
• Surveillance
• Speaker recognition
• Password
• Authentication
• Computer security

SIGNAL PROCESSING MAGAZINE – MANUSCRIPT 1 Speech Segmentation and its Impact on Spoken Document Processing

Source URL: www.cs.nyu.edu

• Systemic functional linguistics
• Phonetics
• Computational linguistics
• Text segmentation
• Speech segmentation
• Speech recognition
• Prosody
• Image segmentation
• Formulaic language
• Word
• Intonation
• Speaker diarisation

Speaker identification evidence: its forms, limitations, and roles Francis Nolan University of Cambridge Cambridge, UK

Source URL: www.ling.cam.ac.uk

• Phonetics
• Forensic linguistics
• Speaker recognition
• Prosody
• Phonetic transcription
• Vowel
• Human voice
• Forensic identification
• Intonation
• Forensic science
• DNA profiling
• Francis Nolan

A study of speaker adaptation for DNN-based speech synthesis Zhizheng Wu Pawel Swietojanski Christophe Veaux Steve Renals

Source URL: homepages.inf.ed.ac.uk

• Automatic identification and data capture
• Computational linguistics
• Computer accessibility
• Speech recognition
• Markov models
• Speech synthesis
• Speaker recognition
• Artificial neural network
• Hidden Markov model
• Vector
• Deep learning

CASE STUDY JUST THE VOICE TO VERIFY THE IDENTITY OF TATRA BANKA CLIENTS COMPANY: Tatra Banka

Source URL: old.soitron.sk

• Biometrics
• Computer access control
• Automatic identification and data capture
• Speaker recognition
• Speech processing
• Authentication
• Card reader
• Tatra banka
• Tatra
• Interactive voice response
• Agnitio

SPEAKER TRAIT CHARACTERIZATION IN WEB VIDEOS: UNITING SPEECH, LANGUAGE, AND FACIAL FEATURES Felix Weninger1 , Claudia Wagner2 , Martin W¨ollmer1,3 , Bj¨orn Schuller1,2 , and Louis-Philippe Morency4 1 Machine Intellige

Source URL: claudiawagner.info

• Humancomputer interaction
• Multimodal interaction
• Computational linguistics
• Modality
• Semantics
• Grammatical moods
• Speech recognition
• Local binary patterns
• Affective computing
• Biometrics
• Linguistic modality
• Dialog system

Intersession compensation and scoring methods in the i-vectors space for speaker recognition Pierre-Michel Bousquet, Driss Matrouf, Jean-Franc¸ois Bonastre University of Avignon (LIA), France {pierre-michel.bousquet, dr

Source URL: mistral.univ-avignon.fr

SCORE CALIBRATING FOR SPEAKER RECOGNITION BASED ON SUPPORT VECTOR MACHINES AND GAUSSIAN MIXTURE MODELS Marcel Katz, Martin Schaff¨oner, Sven E. Kr¨uger, Andreas Wendemuth IESK-Cognitive Systems University of Magdeburg,

Source URL: mistral.univ-avignon.fr

Seminar on Oct 10th Abstracts & speaker information Large-scale Polytonic Greek Optical Character Recognition in Practice and Theory Federico Boschetti (Italy)

Source URL: www.e-humanities.net