Steve Young

Emotion Conversion using F0 Segment Selection (2009)

Zeynep Inanoglu, Steve Young

This paper describes F0 segment selection, a novel syllablebased F0 conversion method, which provides a concatenative framework to search for F0 segments in a modest corpus of emotional speech (∼15...

and Use America’s Living Capital. ” The tools (2009)

Judith Cushing, Tyrone Wilson, Tyrone Wilson, Alan Borning, Lois Delcambre, Anne Fiala, ...

Eco-informatics (sometimes referred to as ecosystem informatics) is the management and analysis of ecological information and the facilitation of large-scale ecological research through the...

The Hidden Vector State Language Model (2009)

Vidura Seneviratne, Steve Young

The Hidden Vector State (HVS) model extends the basic Hidden Markov Model (HMM) by encoding each state as a vector of stack states but with restricted stack operations. The model uses a right...

Being a Man: The Pursuit of Manliness in The Shepherd of Hermas (2009)

Steve Young

Journal of Early Christian Studies - Volume 2, Number 3, Fall 1994

Bootstrapping language models for dialogue systems (2008)

Karl Weilhammer, Matthew N. Stuttle, Steve Young

We report results on rapidly building language models for dialogue systems. Our base line is a recogniser using a grammar network. We show that we can almost halve the word error rate (WER) by...

Repairing Tracheoesophageal Speech Duration Abstract (2008)

Arantza Del Pozo, Steve Young

This paper describes an investigation into the repair of the prosodic limitations of tracheoesophageal (TE) speech. The proposed repair algorithm modifies TE phone durations based on the predictions...

1 Using Wizard-of-Oz simulations to bootstrap Reinforcement-Learningbased dialog management systems (2008)

Jason D. Williams, Steve Young

This paper describes a method for “bootstrapping” a Reinforcement Learningbased dialog manager using a Wizard-of-Oz trial. The state space and action set are discovered through the annotation,...

Training a real-world POMDP-based Dialogue System (2008)

Blaise Thomson, Jost Schatzmann, Karl Weilhammer, Hui Ye, Steve Young

Partially Observable Markov Decision Processes provide a principled way to model uncertainty in dialogues. However, traditional algorithms for optimising policies are intractable except for cases...

BAYESIAN UPDATE OF DIALOGUE STATE FOR ROBUST DIALOGUE SYSTEMS (2008)

Blaise Thomson, Jost Schatzmann, Steve Young

This paper presents a new framework for accumulating beliefs in spoken dialogue systems. The technique is based on updating a Bayesian Network that represents the underlying state of a Partially...

The Application of Hidden Markov Models in Speech Recognition (2008)

Mark Gales, Steve Young

Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech...

1.1 Bootstrapping Statistical Dialogue Managers (2008)

Jost Schatzmann, Blaise Thomson, Karl Weilhammer, Hui Ye, Steve Young

This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simulating user behaviour....

A System for Transforming the Emotion in Speech: Combining Data-Driven Conversion Techniques for Prosody and Voice Quality (2008)

Zeynep Inanoglu, Steve Young

This paper describes a system that combines independent transformation techniques to endow a neutral utterance with some required target emotion. The system consists of three modules that are each...

Statistical User Simulation with a Hidden Agenda (2008)

Jost Schatzmann, Blaise Thomson, Steve Young

Recent work in the area of probabilistic user simulation for training statistical dialogue managers has investigated a new agenda-based user model and presented preliminary experiments with a...

Towards Customizable Individualized Dialogue Systems (2008)

Marilyn Walker, Roger Moore, Steve Whittaker, Johanna Moore, Steve Young, U. Sheffield Speech

Spoken language dialogue systems are one of the few extant examples of an intelligent artifact that can interact with humans. As such, they provide a platform for exploring fundamental cognitive...

DOI: 10.1017/S000000000000000 Printed in the United Kingdom A Survey of Statistical User Simulation Techniques for Reinforcement-Learning of Dialogue Management Strategies (2008)

Jost Schatzmann, Karl Weilhammer, Matt Stuttle, Steve Young

Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the...

and Use America’s Living Capital. ” The tools (2008)

Judith Cushing, Tyrone Wilson, Tyrone Wilson, Alan Borning, Lois Delcambre, Anne Fiala, ...

Eco-informatics (sometimes referred to as ecosystem informatics) is the management and analysis of ecological information and the facilitation of large-scale ecological research through the...

Francine Berman (2007)

Shava Smallen, Mei-hui Su, Walfredo Cirne, Carl Kesselman, Jaime Frey, Steve Young, ...

Computational Grids are becoming an increasingly important and powerful platform for the execution of largescale, resource-intensive applications. However, it remains a challenge for applications to...

and (2007)

Steve Young

dialogue simulation for automatic strategy learning

"Low"-Temperature Reactivities of Ultra-High Temperature Ceramics (Hf-X System) (2006)

Blum, Yigal, Hornbostel, Marc, MacQueen, D. B., Hui, David, Young, Steve, Marschall, Jochen, ...

A growing interest in ultra high temperature ceramics and their aerospace and turbine applications has led to a renewal of activities to fabricate MB2/SiC composites as the materials of choice,...

For copies of reports, updates on project activities and other TALK-related information, contact: (2006)

Karl Weilhammer, Rebecca Jonson, Aarne Ranta, Matt Stuttle, Steve Young, ...

Project funded by the European Community under the Sixth Framework Programme for Research and Technological Development The deliverable identification sheet is to be found on the reverse of this...

For copies of reports, updates on project activities and other TALK-related information, contact: (2006)

Steve Young, Jason Williams, Jost Schatzmann, Matt Stuttle, Karl Weilhammer, ...

Project funded by the European Community under the Sixth Framework Programme for Research and Technological Development The deliverable identification sheet is to be found on the reverse of this...

Using POMDPs for dialog management (2006)

Steve Young

This paper explains how partially observable Markov decision processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialog systems. It...

Using POMDPs for dialog management (2006)

Steve Young

This paper explains how partially observable Markov decision processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialog systems. It...

For copies of reports, updates on project activities and other TALK-related information, contact: (2006)

Karl Weilhammer, Rebecca Jonson, Jost Schatzmann, Matt Stuttle, Steve Young, ...

Project funded by the European Community under the Sixth Framework Programme for Research and Technological Development The deliverable identification sheet is to be found on the reverse of this...

Quality-Enhanced Voice Morphing Using Maximum Likelihood Transformations (2006)

Hui Ye, Student Member, Steve Young

Abstract — Voice morphing is a technique for modifying a source speaker’s speech to sound as if it was spoken by some designated target speaker. The core process in a voice morphing system is the...

Semantic Processing using the Hidden Vector State Model (2005)

Yulan He, Steve Young

This paper discusses semantic processing using the Hidden Vector State (HVS) model. The HVS model extends the basic discrete Markov model by encoding context in each state as a vector. State...

The hidden information state approach to dialogue management (2005)

Steve Young, Jost Schatzmann, Karl Weilhammer, Hui Ye

Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for modelling the uncertainty inherent in spoken dialog systems. However, conventional POMDPs scale...

Factored Partially Observable Markov Decision Processes for Dialogue Management (2005)

Jason D. Williams, Pascal Poupart, Steve Young

This work shows how a dialogue model can be represented as a factored Partially Observable Markov Decision Process (POMDP). The factored representation has several benefits, such as enabling more...

Effects of the User Model on Simulation-Based Learning of Dialogue Strategies (2005)

Jost Schatzmann, Matthew N. Stuttle, Karl Weilhammer, Steve Young

Over the past decade, a variety of user models have been proposed for user simulation-based reinforcement-learning of dialogue strategies. However, the strategies learned with these models are rarely...

Factored partially observable Markov decision processes for dialogue management (2005)

Jason D. Williams, Pascal Poupart, Steve Young

This work shows how a dialogue model can be represented as a factored Partially Observable Markov Decision Process (POMDP). The factored representation has several benefits, such as enabling more...

Using Factored Partially Observable Markov Decision Processes with Continuous Observations for Dialog Management (2005)

J. D. Williams, P. Poupart, S. Young, Jason D. Williams, Pascal Poupart, Steve Young

Table of Contents ABSTRACT.................................................................................................................................................. 5

Factored partially observable Markov decision processes for dialogue management (2005)

Supervisor Prof, Steve Young, Jason D. Williams, Jason D. Williams

While numerous models of human/human conversation have been proposed and evaluated, human/computer conversation currently lacks a model which accounts well for the increased uncertainty introduced by...

Characterizing task-oriented dialog using a simulated ASR channel (2004)

Jason D. Williams, Steve Young

We describe a data collection consisting of task-oriented human-human conversations in a simulated ASR channel in which the WER is systematically varied. We find that users infrequently give a direct...

A framework for dialogue data collection with a simulated asr channel (2004)

Matthew N. Stuttle, Jason D. Williams, Steve Young

The application of machine learning methods to the dialogue management component of spoken dialogue systems is a growing research area. Whereas traditional methods use handcrafted rules to specify a...

Robustness Issues in a Data-Driven Spoken Language Understanding System (2004)

Yulan He, Steve Young

Robustness is a key requirement in spoken language understanding (SLU) systems. Human speech is often ungrammatical and ill-formed, and there will frequently be a mismatch between training and test...

Characterizing Task-Oriented Dialog using a Simulated ASR Channel (2004)

Jason Williams And, Jason D. Williams, Steve Young

We describe a data collection consisting of task-oriented human-human conversations in a simulated ASR channel in which the WER is systematically varied. We find that users infrequently give a direct...

A Framework for Dialogue Data Collection with a Simulated ASR Channel (2004)

Matthew Stuttle Jason, Jason D. Williams, Steve Young

The application of machine learning methods to the dialogue management component of spoken dialogue systems is a growing research area. Whereas traditional methods use handcrafted rules to specify a...

A data-driven spoken language understanding system (2003)

Yulan He, Steve Young

This paper presents a purely data-driven spoken language understanding (SLU) system. It consists of three major components, a speech recognizer, a semantic parser, and a dialog act decoder. A novel...

The Statistical Approach to the Design of Spoken Dialogue Systems (2002)

Steve Young

this technical report is to explore the extent to which the paradigm used for speech recognition can be extended to cover the design and implementation of complete spoken dialogue systems

Statistical modelling in continuous speech recognition (2001)

Steve Young, England Cb Pz

Automatic continuous speech recognition (CSR) is suciently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues....

Probabilistic methods in spoken dialogue systems (2000)

Steve Young

This paper presents a probabilistic framework for modelling spoken dialogue systems. On the assumption that the overall system behaviour can be represented as a Markov Decision Process, the...

Combining Workstations and Supercomputers to Support Grid Applications: The Parallel Tomography Experience (2000)

Shava Smallen, Walfredo Cirne, Jaime Frey, Francine Berman, Rich Wolski, Mei-Hui Su, ...

Computational Grids are becoming an increasingly important and powerful platform for the execution of largescale, resource-intensive applications. However, it remains a challenge for applications to...

Probabilistic Simulation Of Human-Machine Dialogues (2000)

Konrad Scheffler, Steve Young

The field of spoken dialogue systems has developed rapidly in recent years. However, optimisation, evaluation and rapid development of systems remain problematic. This paper describes a method of...

Combining Workstations and Supercomputers to Support Metacomputing Applications: The Parallel Tomography Experience (2000)

Walfredo Cirne, Jaime Frey, Shava Smallen, Francine Berman, Rich Wolski, Steve Young, ...

Resource-intensive parallel applications are typically developed to target either workstation clusters or parallel supercomputers. In this paper, we describe a strategy that leverages the advantages...

Combining Workstations and Supercomputers to Support Grid Applications: The Parallel Tomography Experience (2000)

Shava Smallen Walfredo, Walfredo Cirne, Jaime Frey, Rich Wolski, Mei-hui Su, Carl Kesselman, ...

Computational Grids are becoming an increasingly important and powerful platform for the execution of large-scale, resource-intensive applications. However, it remains a challenge for applications to...

Modelling speaking rate using a between frame distance metric (1999)

Andreas Tuerk, Steve Young

It is well known [5] that variations in speaking rate can account for a significant percentage of errors in practical speech recognition tasks. This is the result of the dynamic nature of speech...

Development of Methods to Generate High Resolution Climatological Databases to Support DoD Modeling and Simulation Programs (1998)

Zack, John W., Van Knowe, Glenn E., Price, Pamela E., Bousquet, Mary D., Young, Steve

This project focuses on developing methods to estimate climate statistics at high resolution in data sparse and data rich locations. The method, given the name CLIMOD, is based on the use of a...

Language Learning Based On Non-Native Speech Recognition (1997)

Silke Witt, Steve Young

This work presents methods of assessing non-native speech to aid computer-assisted pronunciation teaching. These methods are based on automatic speech recognition (ASR) techniques using Hidden Markov...

Computer-assisted Pronunciation Teaching based on Automatic Speech Recognition (1997)

Silke Witt, Steve Young

Pronunciation teaching methods, as a part of computer assisted language learning systems, are currently limited in their ability to produce feedback on pronunciation quality. After an overview of...

WSJCAM0 Corpus and Recording Description (1994)

Jeroen Fransen, Dave Pye, Tony Robinson, Phil Woodland, Steve Young

this document is the UK English equivalent of a subset of the US American English WSJ0 database [1]

WSJCAM0 Corpus and Recording Description style. Therefore a modified pronunciation dictionary had to be constructed that covered (1994)

Phil Woodl, Steve Young

of the US American English WSJ0 database [1]. The name of the UK English version, WSJCAM0, represents the Wall Street Journal recorded at the University of CAMbridge (phase 0). It consists of...

Report on Review (1993)

Steve Young

Considerable progress has been made in speech recognition technology over the last few years and nowhere has this progress been more evident than in the area of Large Vocabulary Recognition (LVR)....

Report on Review (1993)

Steve Young, Gerrit Bloothooft (editors, Technology Series, Edited Nancy Ide, Jean Vronis, Rebecca Bruce

The past three decades have seen a steady growth of interest in corpus-based techniques for speech and natural language processing. Beginning with the success of the early Markov chain-based speech...

HIV-1 integrase inhibitors that compete with the target DNA substrate define a unique strand transfer conformation for integrase

Espeseth, Amy S., Felock, Peter, Wolfe, Abigail, Witmer, Marc, Grobler, Jay, Anthony, Neville, ...

Diketo acids such as L-731,988 are potent inhibitors of HIV-1 integrase that inhibit integration and viral replication in cells. These compounds exhibit the unique ability to inhibit the strand...

Diketo acid inhibitor mechanism and HIV-1 integrase: Implications for metal binding in the active site of phosphotransferase enzymes

Grobler, Jay A., Stillmock, Kara, Hu, Binghua, Witmer, Marc, Felock, Peter, Espeseth, Amy S., ...

The process of integrating the reverse-transcribed HIV-1 DNA into the host chromosomal DNA is catalyzed by the virally encoded enzyme integrase (IN). Integration requires two metal-dependent...

HIV-1 integrase inhibitors that compete with the target DNA substrate define a unique strand transfer conformation for integrase

Espeseth, Amy S., Felock, Peter, Wolfe, Abigail, Witmer, Marc, Grobler, Jay, Anthony, Neville, ...

Diketo acids such as L-731,988 are potent inhibitors of HIV-1 integrase that inhibit integration and viral replication in cells. These compounds exhibit the unique ability to inhibit the strand...

Diketo acid inhibitor mechanism and HIV-1 integrase: Implications for metal binding in the active site of phosphotransferase enzymes

Grobler, Jay A., Stillmock, Kara, Hu, Binghua, Witmer, Marc, Felock, Peter, Espeseth, Amy S., ...

The process of integrating the reverse-transcribed HIV-1 DNA into the host chromosomal DNA is catalyzed by the virally encoded enzyme integrase (IN). Integration requires two metal-dependent...

Predictor Variables for a Positive Long-Term Functional Outcome in Patients with Acute and Chronic Neck and Back Pain Treated with a McKenzie Approach: A Secondary Analysis

May, Stephen, Gardiner, Eric, Young, Steve, Klaber-Moffett, Jennifer

A cognitive behavioral approach was previously compared to a biomechanical approach (the McKenzie method) for the treatment of patients with back and neck pain in a randomized trial. Few differences...