UK Speech

UK Speech organises one-day meetings, workshops and courses for researchers working in speech science & technology and allied areas.

¤ UK Speech

¤ Home
¤ Programme
¤ Abstracts
¤ Travel
¤ Register
¤ Contact

Internet links:
¤ UEA Comp. Sci.
¤ UCL Phon. & Ling.
¤ Surrey CVSSP

One-day meeting for young speech researchers, 16 July 2008, U. Surrey, Guildford

 [ Home | Programme | Abstracts | Travel | Register | Contact ]

Programme overview

The printed version of the proceedings, which includes abstracts, is also available for download (pdf, bib).

10:00-10:30Coffee and badges available
10:30-11:55Posters 1
11:55-12:00Welcome to Surrey and introduction
12:00-13:00Talks 1: Korin Richmond, Chandra Raut, Catherine Breslin
14:15-15:15Talks 2: Abeer Alwan, Eng-Jon Ong, Gregor Hofer
15:15-15:20Closing remarks and announcements
15:20-17:00Demos and tea
15:30-17:00Posters 2

Programme in detail

 Posters 110:30am - 11:55am 
A1Application of Weighted Finite-State Transducers to Improve Recognition Accuracy for Dysarthric SpeechOmar Caballero, Stephen CoxUniversity of East Anglia
A2Covariance Modelling for Noise-Robust Speech RecognitionRC van Dalen, MJF GalesCambridge University Engineering Department
A3A Shrinkage Estimator for Speech Recognition with Full Covariance HMMsPeter Bell, Simon KingEdinburgh University
A4Longitudinal study of ASR performance on ageing VoicesRavichander Vipperla, Steve Renals, Joe FrankelCSTR, Edinburgh University
A53D video analysis of emotional speechNataliya Nadtoka, James Edge, Adrian Hilton, Philip JacksonCVSSP, University of Surrey
A6Audiovisual Emotion Recognition in an English DatabaseSanaul Haq, Philip JB Jackson, James EdgeCVSSP, University of Surrey
A8Joint Quantization Strategies for Low Bit-Rate Sinusoidal CodingEmre Unver, Stephane Villette, Ahmet KondozCCSR, University of Surrey
A9Non-acoustic Speech InterfaceSertan Kaymak, Stephane Villette, Ahmet KondozCCSR, University of Surrey
A10Unsupervised Feature Vector Normalization with Combined Standard and Throat Microphones for Robust ASRLuis Buera, Antonio Miguel, Oscar Saz, Alfonso Ortega, Eduardo LleidaToshiba Research Europe
A11Audio-based alignment of pre-production videoSiripinyo Chantamunee, Yoshihiko GotohUniversity of Sheffield
A12Tense and lax vowels as a consequence of speech embodimentPiers Messum 
A13The speech of our cousins and our ancestorsAntoine Serrurier, Anna BarneyISVR, University of Southampton
A14Speech recognition using non-linear trajectories in a formant-based articulatory layer of a multiple-level segmental HMMHongwei Hu, Martin J RussellUniversity of Birmingham
 Talks 112:00pm - 1:00pmMark Huckvale, chair
B1Exploiting articulation in speech technologyKorin RichmondCSTR, Edinburgh University
B2Instantaneous Unsupervised Adaptation using Discriminative Mapping TransformsChandra Raut, Kai Yu, Mark JF GalesCambridge University Engineering Department
B3Improving Automatic Phone Alignments for Speech SynthesisCatherine BreslinToshiba Research Europe
 Talks 22:15pm - 3:15pmStephen Cox, chair
C1Rapid Speaker Adaptation with Limited DataAbeer AlwanUniversity of California, Los Angeles
C2Robust Lip-Tracking using Rigid Flocks of Selected Linear PredictorsEng-Jon Ong, Richard BowdenCVSSP, University of Surrey
C3Speech-driven Lip Motion Generation with a Trajectory HMMGregor Hofer, Junichi Yamagishi, Hiroshi ShimodairaCSTR, Edinburgh University
 Demos3:20pm - 5:00pm 
D1Sound Source Localisation, Acoustic Source Separation and Binaural Audio ProcessingBanu GunelCCSR, University of Surrey
D2Quality Evaluation of Spatial Transmission and Reproduction by an Artificial ListenerMartin Dewhirst, Rob ConettaCVSSP/IoSR, University of Surrey
D33D Capture of Dynamic Speech MovementsJames EdgeCVSSP, University of Surrey
 Posters 23:30pm - 5:00pm 
E1Automatic Video Language IdentificationJacob L Newman, Stephen J CoxUniversity of East Anglia
E2A Generalised Derivative Kernel for Speaker VerificationC Longworth, MJF GalesCambridge University Engineering Department
E3Direct Posterior-Based Confidence Measurement for Spoken Term DetectionDong Wang, Joe Frankel, Simon KingCSTR, Edinburgh University
E4HMM-based synthesis of child speechOliver Watts, Junichi Yamagishi, Kay Berkling, Simon KingCSTR, Edinburgh University
E5Articulatory resynthesis of EMA dataIngmar Steiner, Korin RichmondCSTR, Edinburgh University
E6A Novel Multi stage Approach For Blind Separation of Convolutive Speech MixturesTariqullah Jan, Wenwu Wang, DeLiang WangCVSSP, University of Surrey; Ohio State University
E7Towards deriving compact and meaningful articulatory representations: an analysis of feature extraction techniquesVeena D Singampalli, Philip JB JacksonCVSSP, University of Surrey
E8Parallel model combination and digit recognition with soccer audioJ Longton, Philip JB JacksonCVSSP, University of Surrey
E9Voice Impersonation and Speaker RecognitionZargham Haider,Stephane Villette, Ahmet KondozCCSR, University of Surrey
E10Index assignment based channel coding for speech/audio communicationsHuseyin Oztoprak, Stephane Villette, Ahmet KondozCCSR, University of Surrey
E11Synthesising personalised voices for individuals with progressive speech lossSarah Creer, Phil Green, Stuart CunninghamUniversity of Sheffield
E12Cross-language Voice Conversion: Analysis from a Phonetic PerspectiveKayoko Yanagisawa, Mark HuckvaleUCL
E13The Development of the "TalkMaths" Speech Interface at Kingston UniversityAngela Wigmore, Gordon Hunter, Eckhard Pflügel, James Denholm-PriceKingston University


© 2005-7 Mark Huckvale, UCL Last updated by Philip Jackson, 15 July 2008
Valid CSS! This site uses
Cascading Style Sheets.