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.ed.ac.uk

• Artificial intelligence
• Automatic identification and data capture
• Artificial neural networks
• Machine learning
• Computational neuroscience
• Learning
• Humancomputer interaction
• Speech recognition
• Convolutional neural network
• Speaker recognition
• Neocognitron
• Unsupervised learning

PRESS RELEASE KeyLemon secures Series A Investment Martigny, Switzerland, 2nd September 2013 – KeyLemon, a leading provider of face and speaker recognition solutions for authentication purposes, has closed a Series A

Source URL: www.keylemon.com

Influence of speaker familiarity on blind and visually impaired children’s perception of synthetic voices in audio games Michael Pucher1 , Markus Toman1 , Dietmar Schabus1 , Cassia Valentini-Botinhao2 Junichi Yamagishi

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

• Computational linguistics
• Human communication
• Humancomputer interaction
• Software
• Assistive technology
• Speech synthesis
• Speech recognition
• Speech perception
• Audio game
• Labyrinth

DEVELOPING A SPEAKER IDENTIFICATION SYSTEM FOR THE DARPA RATS PROJECT

Source URL: www.fit.vutbr.cz

• Signal processing
• Computational linguistics
• Estimation theory
• Computing
• Statistics
• Electrical engineering
• Speech recognition
• Digital signal processing
• Voice activity detection
• Support vector machine
• Machine learning
• Linear prediction

APSIPA ASC 2011 Xi’an Fast Speaker Normalization and Adaptation based on BIC for Meeting Speech Recognition ∗

Source URL: www.ar.media.kyoto-u.ac.jp

EXPERIMENTS IN BROADCAST NEWS TRANSCRIPTION P.C. Woodland, T. Hain, S.E. Johnson, T.R. Niesler, A. Tuerk & S.J. Young Cambridge University Engineering Department, Trumpington Street, Cambridge, CB2 1PZ, UK e-mail: pcw,th

Source URL: mi.eng.cam.ac.uk

• Speech recognition
• Speech processing
• Science
• Digital signal processing
• Image processing
• Segmentation
• Acoustic model
• Memory segmentation
• Speaker recognition
• Computational linguistics
• Automatic identification and data capture
• Human–computer interaction

OVERVIEW Government Solutions The need to analyze data gathered from low-quality telephony audio sources,

Source URL: www.nexidia.com

• Internet search engines
• Computational linguistics
• Searching
• Speech recognition
• Search engine indexing
• Audio search engine
• Web search engine
• Speaker recognition
• Audio mining
• Information science
• Information retrieval
• Automatic identification and data capture

Self based on the body Speaker: Akira MURATA 1. Introduction Recently, it is claimed that recognition of the body is important for the social cognitive function (joint attention, imitation, communication, mind reading, e

Source URL: www.jsps.go.jp

Peter Schweizer will be our Key Note speaker.  He recently gained national recognition after writing his most recent book, “Throw Them All Out: How Politicians and Their Friends Get Rich off Insider Stock Tips, Land D

Source URL: wakullacountychamber.com

Sequence Kernels for Speaker and Speech Recognition Mark Gales - work with Martin Layton, Chris Longworth, Federico Flego 8 JulyCambridge University Engineering Department

Source URL: mi.eng.cam.ac.uk