Portrait of Dr. Henter Position: Post-doctoral researcher
The Centre for Speech Technology Research
The University of Edinburgh
E-mail: gustav.henter at ed ac uk
Address: Informatics Forum room 3.42
10 Crichton Street
Edinburgh
EH8 9AB
UNITED KINGDOM

Notice

In August 2016, I will leave Edinburgh to take up a post-doc position under Prof. Junichi Yamagishi in the Digital Content and Media Sciences Research Division at the National Institute of Informatics, Tokyo, Japan.

Research

My scientific interests are broad. My current research focus is statistical speech synthesis, where I am particularly interested in the effect of modelling assumptions on speech perception, and in speech synthesis from big data and found data.

Data releases

  1. Gustav Eje Henter, Thomas Merritt, Matt Shannon, Catherine Mayo, and Simon King (2014)
    Repeated Harvard Sentence Prompts (REHASP) corpus version 0.5
    Studio recordings of 30 Harvard sentences, each read aloud 40 times by a female native speaker of British English. Released under a CC BY 4.0 license.
    [ official repository | readme file | publication ]

Journal papers

  1. Gustav Eje Henter and W. Bastiaan Kleijn (2016)
    Minimum entropy rate simplification of stochastic processes
    accepted for publication in IEEE T. Pattern Anal.
    [ postprint | publisher | appendices | abstract | .bib ]
  2. Arne Leijon, Gustav Eje Henter, and Martin Dahlquist (2016)
    Bayesian analysis of phoneme confusion matrices
    IEEE/ACM T. Audio Speech (vol. 24, no. 3, pp. 469–482)
    [ postprint | publisher | abstract | .bib ]
  3. Petko N. Petkov, Gustav Eje Henter, and W. Bastiaan Kleijn (2013)
    Maximizing phoneme recognition accuracy for enhanced speech intelligibility in noise
    IEEE T. Audio Speech (vol. 21, no. 5, pp. 1035–1045)
    [ postprint | publisher | abstract | .bib ]
  4. Gustav Eje Henter and W. Bastiaan Kleijn (2013)
    Picking up the pieces: Causal states in noisy data, and how to recover them
    Pattern Recogn. Lett. (vol. 34, no. 5, pp. 587–594)
    [ postprint | publisher | supplement | abstract | .bib ]

Conference papers

  1. Takenori Yoshimura, Gustav Eje Henter, Oliver Watts, Mirjam Wester, Junichi Yamagishi, and Keiichi Tokuda (2016)
    A hierarchical predictor of synthetic speech naturalness using neural networks
    accepted for presentation at Interspeech 2016
    [ contact me for preprint ]
  2. Srikanth Ronanki, Gustav Eje Henter, Zhizheng Wu, and Simon King (2016)
    A template-based approach for speech synthesis intonation generation using LSTMs
    accepted for presentation at Interspeech 2016
    [ contact me for preprint ]
  3. Mirjam Wester, Oliver Watts, and Gustav Eje Henter (2016)
    Evaluating comprehension of natural and synthetic conversational speech
    Proc. Speech Prosody 2016 (pp. 736–740)
    [ publisher (open access) | abstract | .bib | poster by Dr. Wester ]
  4. Gustav Eje Henter, Srikanth Ronanki, Oliver Watts, Mirjam Wester, Zhizheng Wu, and Simon King (2016)
    Robust TTS duration modelling using DNNs
    Proc. ICASSP 2016 (pp. 5130–5134)
    [ postprint | publisher | abstract | .bib | listening examples | slides w/ audio ]
  5. Oliver Watts, Gustav Eje Henter, Thomas Merritt, Zhizheng Wu, and Simon King (2016)
    From HMMs to DNNs: where do the improvements come from?
    Proc. ICASSP 2016 (pp. 5505–5509)
    [ postprint | publisher | abstract | .bib | poster by Dr. Watts ]
  6. Rasmus Dall, Sandrine Brognaux, Korin Richmond, Cassia Valentini-Botinhao, Gustav Eje Henter, Julia Hirschberg, Junichi Yamagishi, and Simon King (2016)
    Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis
    Proc. ICASSP 2016 (pp. 5155–5159)
    [ postprint | publisher | abstract | .bib | slides by Mr. Dall ]
  7. Mirjam Wester, Cassia Valentini-Botinhao, and Gustav Eje Henter (2015)
    Are we using enough listeners? No! An empirically-supported critique of Interspeech 2014 TTS evaluations
    Proc. Interspeech 2015 (pp. 3476–3480)
    [ postprint | publisher (open access) | abstract | .bib | slides by Dr. Wester ]
  8. Gustav Eje Henter, Thomas Merritt, Matt Shannon, Catherine Mayo, and Simon King (2014)
    Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech
    Proc. Interspeech 2014 (pp. 1504–1508)
    [ postprint | publisher (open access) | abstract | .bib | database | listening examples | slides w/ audio ]
  9. Matthew P. Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, and Thomas Merritt (2014)
    A flexible front-end for HTS
    Proc. Interspeech 2014 (pp. 1283–1287)
    [ postprint | publisher (open access) | abstract | .bib | .odp slides by Mr. Dall ]
  10. Petko N. Petkov, W. Bastiaan Kleijn, and Gustav Eje Henter (2012)
    Enhancing subjective speech intelligibility using a statistical model of speech
    Proc. Interspeech 2012 (pp. 166–169)
    [ postprint | publisher (open access) | abstract | .bib | poster ]
  11. Gustav Eje Henter, Marcus R. Frean, and W. Bastiaan Kleijn (2012)
    Gaussian process dynamical models for nonparametric speech representation and synthesis
    Proc. ICASSP 2012 (pp. 4505–4508)
    [ postprint | publisher | abstract | .bib | poster ]
  12. Gustav Eje Henter and W. Bastiaan Kleijn (2011)
    Intermediate-state HMMs to capture continuously-changing signal features
    Proc. Interspeech 2011 (pp. 1817–1820)
    [ postprint | publisher (open access) | abstract | .bib | poster ]
  13. Gustav Eje Henter and W. Bastiaan Kleijn (2010)
    Simplified probability models for generative tasks: a rate-distortion approach
    Proc. EUSIPCO 2010 (pp. 1159–1163)
    [ postprint | publisher (open access) | abstract | .bib | poster ]

Thesis

  1. Gustav Eje Henter, supervised by W. Bastiaan Kleijn and Arne Leijon (2013)
    Probabilistic sequence models with speech and language applications
    Ph.D. thesis, School of Electrical Engineering, KTH Royal Institute of Technology
    [ official record | abstract | introduction | .bib ]

You can also download my curriculum vitæ and a .bib file with all my publications.