...

Hi! I’m Eddy Pei-Hao Su

Doctoral student in Dialogue, NLP and RL
About

About Me

I'm Pei-Hao Su (蘇培豪), a third year PhD candidate on Statistical Spoken Dialogue Systems at Cambridge University supervised by Professor Steve Young and Dr. Milica Gašić.
I am a Cambridge Trust Scholar, funded by Taiwan Cambridge Scholarship, and a member of Queens' College.

My primary research interest lies mainly in the intersection of deep learning and reinforcement learning for spoken dialogue systems, aiming to set up an unified framework for language understanding/replying and a system that is capable of scaling to broad domains and directly learn from human user interaction.

Prior to Cambridge, I received my Bachelor and Master degree in EECS from National Taiwan University, where I joined the Digital Speech Processing Laboratory held by Professor Lin-shan Lee and focused on statistical dialogue modelling for personalising pronunciation training in a dialogue game.

Curriculum Vitae [] (last update: 1 December 2016)

Awards

  • Best Student Paper Award, ACL, 2016
  • W. G. Collins Endowment Fund Award, Cambridge University Engineering Dept., 2016
  • Interspeech Travel Grant, ISCA, 2015
  • Taiwan Cambridge Scholarship, Cambridge Trust & MOE of Taiwan, 2014-17
  • Government Scholarship for Studying Abroad (waived), MOE of Taiwan, 2014
  • ICASSP Travel Grant, National Science Council of Taiwan, 2013
  • Advanced Speech Technologies Scholarship, NTU EECS Department, 2012
  • Best Intern, Trend Micro Inc., 2012
  • Dean's List, NTU, 2008

Education & jobs

Oct 2014 - University of Cambridge PhD student in Engineering
Advisor: Professor Steve Young
Summer 2012 Trend Micro Inc, Taiwan Software Engineer Intern
Cloud storage division
Jan 2012 - June 2013 National Taiwan University M.Sc. in Communication Engineering
Advisor: Professor Lin-shan Lee
June 2007 - Jan 2012 National Taiwan University B.Sc. in Electrical Engineering
Publication
First author and main work only, see also my full list of publications in my Google Scholar page

Journal Article

  1. “A Recursive Dialogue Game for Personalized Computer-Aided Pronunciation Training”

    IEEE Transaction on Audio, Speech and Language Processing, January 2015 [paper ] [bib ]

    Pei-hao Su, Chuan-hsun Wu, and Lin-shan Lee

Preprint

  1. “Continuously Learning Neural Dialogue Management”

    arXiv preprint:1606.02689 [paper ] [bib ]

    Pei-Hao Su, Milica Gašić, Nikola Mrkšić, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen and Steve Young,

Conference Paper

  1. “On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems” ACL 2016

    [paper ] [bib ] [slides ] [data ] [video ] (Best Student Paper Award)

    Pei-Hao Su, Milica Gašić, Nikola Mrkšić, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen and Steve Young

  2. “Multi-Domain Dialogue Success Classifiers for Policy Training” ASRU 2015

    David Vandyke, Pei-Hao Su, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen and Steve Young

  3. “Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems” SigDial 2015

    [paper ] [bib ]

    Pei-Hao Su, David Vandyke, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen and Steve Young

  4. “Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems” Interspeech 2015

    [paper ] [bib ]

    Pei-Hao Su, David Vandyke, Milica Gašić, Dongho Kim, Nikola Mrkšić, Tsung-Hsien Wen and Steve Young

  5. “A Cloud-based Personalized Recursive Dialogue Game System for Computer-Assisted Language Learning” SLaTE 2013

    [paper ] [bib ]

    Pei-hao Su, Tien-han Yu, Ya-Yunn Su, and Lin-shan Lee

  6. “NTU Chinese 2.0: A Personalized Recursive Dialogue Game for Computer-Assisted Language Learning” SLaTE Demo 2013

    [poster ] [bib ]

    Pei-hao Su, Tien-han Yu, Ya-Yunn Su, and Lin-shan Lee

  7. “A Recursive Dialogue Game Framework with Optimal Policy Offering Personalized Computer-Assisted Language Learning” Interspeech 2013

    [paper ] [bib ]

    Pei-hao Su, Yow-Bang Wang, Tsung-Hsien Wen, Tien-han Yu, and Lin-shan Lee

  8. “A Dialogue Game Framework with Personalized Training using Reinforcement Learning for Computer-Assisted Language Learning” ICASSP 2013

    [paper ] [bib ]

    Pei-hao Su, Yow-Bang Wang, Tien-han Yu, and Lin-shan Lee

Collaborated Conference Paper

  1. “Multi-agent learning in multi-domain spoken dialogue systems”

    NIPS 2015 Workshop on Machine Learning for Spoken Language Understanding and Interaction [paper ]

    Milica Gašić, Nikola Mrkšić, Lina Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen and Steve Young

  2. “Hyper-parameter Optimisation of Gaussian Process Reinforcement Learning for Statistical Dialogue Management” SigDial 2015

    [paper ]

    Lu Chen, Pei-Hao Su and Milica Gašić

Thesis

  1. “A Dialogue Game Framework Offering Personalized Pronunciation Training for Computer-Assisted Language Learning”

    Master Thesis, National Taiwan University 2013

    Pei-hao Su

Talk

Industy

  • "Reward Estmiation for Dialogue Policy Optimisation"

    General Motor Advanced Techinal Center Israel, 20 March 2017

  • “Practical Human-in-the-loop Reinforcement Learning in Spoken Dialogue Systems”

    Apple Cambridge, 12 Oct 2016

  • “On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems”

    Maluuba Research (Now Microsoft). 2 Aug 2016

  • “On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems”

    Toshiba Research Cambridge. 8 June 2016

Academia

  • “Beyond Siri: towards fully data-driven conversational systems”

    Queens' College Cambridge Grad Talk. 20 Feb 2017

  • “On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems”

    Cambridge NLIP Seminar. 25 Nov 2016

  • “Practical and Scalable Reinforcement Learning for Spoken Dialogue Systems”

    NTU Speech Lab, Taiwan. 24 June 2016

  • “Practical and Scalable Reinforcement Learning for Spoken Dialogue Systems”

    Academia Sinica Taiwan. 21 June 2016

  • “Transfer Learning”

    Cambridge University Machine Learning Group Seminar. Feb 2015, with Yingzhen Li, [slide ]

Conference

  • “On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems”

    ACL 2016. Berlin, Germany.

  • “Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems”

    Interspeech 2015. Dresden, Germany.

  • “A Cloud-based Personalized Recursive Dialogue Game System for Computer-Assisted Language Learning”

    SLaTE 2013. Grenoble, France.

  • “A Recursive Dialogue Game Framework with Optimal Policy Offering Personalized Computer-Assisted Language Learning”

    Interspeech 2013. Lyon, France.

  • “A Dialogue Game Framework with Personalized Training using Reinforcement Learning for Computer-Assisted Language Learning”

    ICASSP 2013. Vancouver, Canada.

Teaching

Teaching Assistant

Spring 2017 Reinforcement Learning MPhil in Machine Learning, Speech and Language Technology, Cambridge University
Fall 2016 Introduction to Python Murray Edwards College, Cambridge University
Spring 2016 Statistical Dialogue Systems MPhil in Machine Learning, Speech and Language Technology, Cambridge University
Spring & Fall 2012, Spring 2013 Digital Speech Processing EECS Department, National Taiwan University
Spring & Fall 2012, Spring 2013 Special Project: Reinforcement Learning for Dialogue Game EECS Department, National Taiwan University

Contact Info

  • Room BN3-011
    Engineering Department
    Trumpington Street
    Cambridge CB2 1PZ
  • phs26@cam.ac.uk
  • +44 1223 332 654

Copyright © 2017 Pei-Hao (Eddy) Su, Design: Mi.