Mark Gales

Mark Gales is a Professor of 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 Phil Woodland and Bill Byrne. Recent past members of the group include Milica Gasic and Steve Young.

A brief biography is available online.

Research interests

• Low Resource Speech Processing - BABEL and MATERIAL projects
• Automatic Assesment of Spoken English - The ALTA Institute (ALTA Spoken Language Processing Technology Project)
• Uncertainty, Generalisation and Interpretability for Deep Learning - Google Research Award
• High Quality Expressive, Controllable and Adaptable Speech Synthesis - HQSTS project
• Large Vocabulary Speech Recognition - MGB Challenge (English)
• Sequence modelling for biomedicine - collaboration with Anurag Agarwal, Acoustics Lab at CUED

If you are interested in studying for a PhD in Spoken Language Processing contact Mark Gales.

top

Research Projects

Current projects:

• ALTA (Cambridge English funded) - local web-page
• Multimodal Video Search by Examples (EPSRC funded)
  Collaboration with Universities of Ulster and Surrey - local web-page
• MATERIAL (IARPA funded) - local web-page
• Maori Langauge Revitilisation (Collaboration with Te Hiku Media)

Software projects:

• CUED RNNLM Toolkit (v1.1 release December 2017)
• Percival TTS CNN-WGAN acoustic model for text-to-speech synthesis (HQSTS project)
• HTK Version 3 - HTK_V3.4.1 and examples are available.
  HTK_V3.5 beta updated 28th June 2016, see UK Speech Presentation for details

Completed projects:

• MGB Challenge (English) (unfunded!) - local web-page
• Automatic Lecture Captioning @CUED (unfunded!) - local web-page
• High-Quality voice model for STatistical parametric speech Synthesis (EU funded) - local web-page
• BABEL (IARPA funded project) - local web-page
• Adaptive Meeting Transcription - PhD Studentship (Toshiba Research Europe Ltd funded)
• Natural Speech Technology (EPSRC funded project) - local web-pages: ASR TTS
• Generative Kernels and Score-Spaces for Classification of Speech (EPSRC funded project)
• Broad Operational Language Translation (DARPA funded project) - local web-page
• Robust Automatic Transcription of Speech (DARPA funded project) - local web-page
• Automatic Oral Communication Skill Evaluation (Cambridge English funded) - local web-page
• Structured Support Vector Machines for Speech Recognition (Toshiba Research Europe Ltd funded)
• Rapid and Robust Environment Aware Processing (Toshiba Research Europe Ltd funded)
• AGILE (DARPA GALE funded project)
• HTK Rich Audio Transcription (DARPA EARS funded project) - local web-pages
• CoreTex (Improving Core Speech Recognition technology)

Teaching: 2021-2022

For the Engineering Department:

• MPhil in Machine Learning and Machine Intelligence - local information
  • Spoken Language Processing and Generation (MLMI14)
• Fourth year engineering undergraduates Module 4F10: Deep Learning and Structured Data.
• Fourth year engineering undergraduates Final Year Projects.
• Third year engineering undergraduates Module 3M1: Mathematical Methods.

• Part IB Paper 6: Information Engineering

Contact Information