- EFFICIENT MLLR Matthew Gibson
- LINKING AUDITORY SCENE ANALYSIS AND ROBUST ASR BY MISSING DATA TECHNIQUES
- Robust ASR Based On Clean Speech Models: An Evaluation of Missing Data Techniques For Connected Digit Recognition in Noise
- DECODING SPEECH IN THE PRESENCE OF OTHER SOUND SOURCES Jon Barker, Martin Cooke
- SOFT DECISIONS IN MISSING DATA TECHNIQUES FOR ROBUST AUTOMATIC SPEECH RECOGNITION.
- Modelling speaker intelligibility in noise Jon Barker , Martin Cooke
- ACOUSTIC CONFIDENCE MEASURES FOR SEGMENTING BROADCAST NEWS J. Barker, G. Williams and S. Renals
- FROM MISSING DATA TO MAYBE USEFUL DATA: SOFT DATA MODELLING FOR NOISE ROBUST ASR
- LINKING AUDITORY SCENE ANALYSIS AND ROBUST ASR BY MISSING DATA TECHNIQUES
- IS PRIMITIVE AV COHERENCE AN AID TO SEGMENT THE J.P. Barker, F. Berthommier and J.L. Schwartz
- UNSUPERVISED CROSS-LINGUAL SPEAKER ADAPTATION FOR HMM-BASED SPEECH SYNTHESIS USING TWO-PASS DECISION TREE CONSTRUCTION
- MINIMUM BAYES RISK ACOUSTIC MODEL ESTIMATION AND Matthew Gibson
- Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models
- MISSING DATA SPEECH RECOGNITION IN REVERBERANT CONDITIONS Kalle J. Palomki1,2
- ESTIMATION OF SPEECH ACOUSTICS FROM VISUAL SPEECH FEATURES: A COMPARISON OF LINEAR AND NONLINEAR MODELS.
- DECODING SPEECH IN THE PRESENCE OF OTHER SOUND SOURCES Jon Barker, Martin Cooke
- JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 1 Error approximation and minimum phone error
- The foreign language cocktail party problem: Energetic and informational masking effects in non-native speech
- Temporal Masking for Unsupervised Minimum Bayes Risk Speaker Adaptation Matthew Gibson & Thomas Hain
- A Theory and Computational Model of Auditory Selective Attention
- Energetic and informational masking effects in an audio-visual speech recognition system.
- A SPEECH FRAGMENT APPROACH TO LOCALISING MULTIPLE SPEAKERS IN REVERBERANT ENVIRONMENTS
- ACOUSTIC CONFIDENCE MEASURES FOR SEGMENTING BROADCAST NEWS J. Barker, G. Williams and S. Renals
- Handling Missing and Unreliable Information in Speech Recognition Phil Green, Jon Barker, Martin Cooke, and Ljubomir Josifovski
- A Neural Oscillator Sound Separator for Missing Data Speech Recognition
- A Theory and Computational Model of Auditory Selective Attention
- MODELLING THE RECOGNITION OF SPECTRALLY REDUCED SPEECH Jon Barker and Martin Cooke
- Stream weight estimation for multistream audio-visual speech recognition in a
- JOURNAL OF LATEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 1 Unsupervised intralingual and cross-lingual speaker
- FROM MISSING DATA TO MAYBE USEFUL DATA: SOFT DATA MODELLING FOR NOISE ROBUST ASR
- Speech fragment decoding techniques for simultaneous speaker identification and speech
- Exploiting correlogram structure for robust speech recognition with multiple speech sources
- An automatic speech recognition system based on the scene analysis account of auditory perception
- LETTERS TO THE EDITOR This Letters section is for publishing (a) brief acoustical research or applied acoustical reports, (b)
- Mask estimation for missing data speech recognition based on statistics of binaural interaction
- Decoding speech in the presence of other sources J.P. Barker a,*,1
- COMBINING BOTTOM-UP AND TOP-DOWN CONSTRAINTS FOR ROBUST ASR: THE MULTISOURCE DECODER
- EVIDENCE OF CORRELATION BETWEEN ACOUSTIC AND VISUAL FEATURES OF SPEECH
- The Relationship between Speech Perception and Auditory Organisation: Studies with Spectrally Reduced Speech
- TRACKING FACIAL MARKERS WITH AN ADAPTIVE MARKER COLLOCATION MODEL Department of Computer Science, University of Sheffield
- Using Prosodic Features in Language Models for Meetings
- Analysis of Unsupervised and Noise-Robust Speaker-Adaptive HMM-Based Speech Synthesis Systems toward a Unified ASR and TTS Framework
- Hypothesis Spaces For Minimum Bayes Risk Training In Large Vocabulary Speech Recognition
- Title Full Name Organisation Department Name Groupings International
- Generating German intonation with a trainable prosodic model Grard Bailly Jan Gorisch
- Eligibility Criteria for AHRC Peer Review College Membership The AHRC categorises its peer reviewers into different groups to improve our ability to
- CONDITIONAL RANDOM FIELDS FOR CONTINUOUS SPEECH RECOGNITION
- The CHiME corpus: a resource and a challenge for Computational Hearing in Multisource Environments
- Panel Remits Outlined below is the subject remit of the AHRC's Panels. The primary subject area selected by
- Supporting world class research in the arts and humanities
- Maintenance and Fee Breakdown -Academic Year 2011/12 RATE London Elsewhere London Elsewhere London Elsewhere
- Recent advances in speech fragment decoding techniques Jon Barker, Andre Coy, Ning Ma and Martin Cooke
- IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING , VOL. X, NO. XX, XXXXXXXXX XXXX 1 Recognition of Dialogue Acts in Multiparty
- Social Impact of Artist Exhibitions: Two Case Studies Translations
- It is unlikely that the lexical concept of a word does not have a one to one relationship with spoken Word boundaries were not defined directly by the speech recognition transcript. Instead unit
- A PITCH BASED NOISE ESTIMATION TECHNIQUE FOR ROBUST SPEECH RECOGNITION WITH MISSING DATA
- Robust automatic speech recognition with missing and unreliable acoustic data
- on the right track The AHRC provides funding for
- PASCAL CHiME Challenge: baseline recogniser and scoring scripts Ning Ma (n.ma@dcs.shef.ac.uk), Jon Barker and Heidi Christensen, October 2010 (version 0.1)
- Research Councils UK Polaris House, North Star Avenue
- Term-Weighting for Summarization of Multi-party Spoken Dialogues
- Knowing What You Don't Know: Roles for Confidence Measures in Automatic
- Final Report: GR/T04823/01 Audio-visual speech recognition in the presence of non-stationary noise
- PERCEPTION OF SYNTHETIC CONSONANT-VOWEL STIMULI Viktoria Maier, Hynek Hermansky
- Confidence-informed unsupervised minimum Bayes risk acoustic model adaptation
- Integrating pitch and localisation cues at a speech fragment level Heidi Christensen, Ning Ma, Stuart N. Wrigley, Jon Barker
- 1208 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 6, AUGUST 2009 Robust Speaker-Adaptive HMM-Based
- Institut fr Phonetik und Sprachverarbeitung LUDWIG-MAXIMILIANS-UNIVERSITT MNCHEN
- Speech fragment decoding techniques for simultaneous speaker identification and speech recognition
- Jan Gorisch Personal Information Marital status: Single
- Peer Review Panel Members -Previous 2009 Panels
- Marie Curie Research Training Network S2S Fellows' Career Development Plan
- AHRC Code of Practice CODE OF PRACTICE
- RESPITE CASA Toolkit User's Guide
- Submitted to Robust'99, Tampere, Finland on March 5th 1999 ROBUST ASR WITH UNRELIABLE DATA AND MINIMAL ASSUMPTIONS
- 2011 The University of Sheffield Interacting with Purpose (and Feeling!) slide 1
- From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition
- Context-Dependent Word Duration Modelling for Robust Speech Recognition Ning Ma and Phil Green
- Applying word duration constraints by using unrolled HMMs Ning Ma, Jon Barker, Phil Green
- Peer Review Panel Members -Previous 2010 Panels
- ARTS AND HUMANITIES RESEARCH COUNCIL (AHRC) ROYAL CHARTER
- Mike Hochberg is now at Nuance Communications, 333 Ravenswood Avenue, Building 110, Menlo Park, CA 94025, USA.
- The Case for Case-Based Automatic Speech Recognition Viktoria Maier, Roger K. Moore
- Research Councils UK Polaris House, North Star Avenue
- Version 1, 28/11/2011 Guidance Notes for Off College Peer Reviewers
- Block Grant Partnership (BGP) List of Awards
- Research Councils UK Polaris House, North Star Avenue
- Leadingtheworld The economic impact of UK arts and humanities research
- Connectionist Probability Estimators in HMM Speech Recognition
- Can crime be reduced by making it harder, more risky
- At Home in Renaissance Italy An impact Case Study
- Towards Speaker Independent Features for Information Extraction from Meeting Audio Data
- AHRC Twitter Policy The Arts and Humanities Research Council (AHRC) Twitter account is managed by the press team, on
- Page 1 of 42 Studentship Grants
- Exploiting dendritic autocorrelogram structure to identify spectro-temporal regions dominated by a single sound source
