Mark Gales

Mark Gales is a Reader in Information Engineering in the Machine Intelligence Laboratory (formerly the Speech Vision and Robotics (SVR) group) and a Fellow of Emmanuel College. He is a member of the Speech Research Group together with faculty staff members Steve Young, Phil Woodland and Bill Byrne.

A brief biography is available online.

Research interests

• Large vocabulary continuous speech recognition
• Robust speech recognition
• Speaker adaptation
• Machine learning (particularly model selection and kernel-based methods)
• Speaker identification and verification

Research Projects

• Noise Robust ASR (Toshiba Research Europe Ltd funded)
• Rapid and Robust Environment Aware Processing (Toshiba Research Europe Ltd funded)
• AGILE (DARPA GALE funded project)
• HTK Version 3 - HTK_V3.4 and examples are available.
  

• CoreTex (Improving Core Speech Recognition technology)
• HTK Rich Audio Transcription (DARPA EARS funded project) - local web-pages

Research Students

• Sarah Airey : Product of Experts for Automatic Speech Recognition
• Rogier van Dalen : Noise Robust Speech Recognition (Toshiba project)
• Anton Ragni : Discriminative models for speech (HTK/Toshiba funded)
• Zoi Roupakia : Kernel Methods for Speech Processing
• Eric Wang : Universal Acoustic Models (Google Research Award part-funded)
• Austin Zhang : Structured Discriminative Models

• Catherine Breslin : Complementary System Generation and Combination [pdf]
• Martin Layton : Kernel Methods for Classifying Variable Length Data [pdf]
• Hank Liao : Uncertainty Decoding for Noise Robust Speech Recognition [pdf]
• Andrew Liu : Discriminative Complexity Control and Linear Projections for LVCSR [pdf]
• Chris Longworth : Speaker Verification and Identification using Kernel Methods
• CK Raut : Discriminative Adaptive Training and Bayesian Inference for ASR (sub. Dec 2009)
• Antti-Veikko Rosti : Linear Gaussian models for speech recognition [pdf]
• Khe Chai Sim : Structured Precision Matrix Modelling for Speech Recognition [pdf]
• Nathan Smith : Using augmented statistical models and score spaces for classification [pdf]
• Mathew Stuttle : Formant-like features for speech recognition [pdf]
• Kai Yu : Adaptive Training for LVCSR [pdf]

Teaching (2009-2010)

• Masters in Computer Speech, Text and Internet Technology
  Material available online (local access only)
• Fourth year engineering undergraduates Module 4F10: Statistical Pattern Processing.
  Material available online (local access only)
• Fourth year engineering undergraduate projects to be offered 2009-2010 (local access only).

• Part IB Paper 6: Information Engineering

Contact Information