Skip to main content

Trinity College Dublin, The University of Dublin

Menu Search



John Kane

PLEASE NOTE THAT AS FROM 20TH DECEMBER 2013 THIS SITE IS NO LONGER BEING MAINTAINED

JohnKane

Contact Information

Email: kanejo@tcd.ie
Google Scholar: link LinkedIn: link
Address: Phonetics & Speech Laboratory,
Centre for Language and Communication Studies,
Room 4074 Arts Building,
Trinity College Dublin,
College Green,
Dublin 2

Quicklinks

Research Interests

Glottal source and voice quality analysis, expressive speech synthesis, analysis of speaking style variation in spoken interaction.

Current Projects

  • Designing robust strategies for parameterisation of perceptually important aspects of the glottal excitation source.
  • Developing effective and robust approaches for classifying and discriminating voice quality in corpora of expressive speech.
  • Applying these developments to various speech technology applications, e.g., expressive speech synthesis, emotion recognition, detection of disordered speech etc.

Publications

Thesis

  • Kane, J., (2013) `Tools for analysing the voice - Developments in glottal source and voice quality analysis', Ph.D. Thesis (Link)

Journal publications

  • Scherer, S., Kane, J., Gobl, C., Schwenker, F., (2013)
    `Investigating fuzzy-input fuzzy-output support vector machines for robust voice quality classification', Computer Speech and Language 27(1), pp. 263-287 (Link)
  • Kane, J., Gobl, C., (2013) `Evaluation of glottal closure instant detection in a range of voice qualities', Speech Communication 55(2), pp. 295-314. (Link)
  • Kane, J., Drugman, T., Gobl, C., (2013) `Improved automatic detection of creak', 27(4), pp. 1028-1047, Computer Speech and Language. (Link)
  • Kane, J., Gobl, C., (2013) `Automating manual user strategies for precise voice source analysis', Speech Communication 55(3), pp.397-414. (Link)
  • Kane, J., Gobl, C., (2013) `Wavelet maxima dispersion for breathy to tense voice discrimination', IEEE Transactions on Audio Speech and Language Processing, 21(6), pp. 1170-1179. (Link)
  • Kane, J., Aylett, M., Yanushevskaya, I., Gobl, C., [Under review] `Phonetic feature extraction for context sensitive glottal source processing', Speech Communication.
  • Drugman, T., Kane, J., Gobl., C., [Under review] `Data-driven detection and analysis of the patterns of creaky voice', Computer Speech and Language, Special issue on glottal source processing.

Selected conference publications

  • Kane, J., De Looze, C., Yanushevskaya, I., Ní Chasaide, A.,[Submitted] `Analysing the prosodic characteristics of speech-chunks preceding silences in task-based interactions', Proceedings of ICASSP 2014.
  • Raitio, T., Lu, H., Kane, J., King, S., Alku, P., [Submitted] `Voice source modelling using deep neural networks for statistical parametric speech synthesis', Proceedings of ICASSP 2014.
  • Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S., [Submitted] `'
    `COVAREP - A collaborative voice analysis repository for speech technologies', Proceeding of ICASSP 2014.
  • De Looze, C., Kane, J., Yanushevskaya, I., Ní Chasaide, A., [Submitted] `'
    `Characterising passive and active listening and talking state dynamics in spoken interaction', Proceeding of ICASSP 2014.
  • Cullen, A., Kane, J., Drugman, T., Harte, N., (2013)
    `Creaky voice and the classification of affect', Proceeding of WASSS 2013, Grenoble, France. (Paper).
  • Kane, J., Scherer, S., Morency, L-P, , Gobl, C., (2013)
    `A comparative study of glottal open quotient estimation techniques', Interspeech 2013, Lyon, France. (Paper). (Poster).
  • Kane, J., Yanushevskaya, I., Dalton, J., Gobl, C., Ní Chasaide, A., (2013)
    `Using phonetic feature extraction to determine optimal  speech regions for maximising the effectiveness of glottal source analysis', Interspeech 2013, Lyon, France. (Paper). (Slides).
  • Raitio, T., Kane, J., Drugman, T., Gobl, C., (2013)
    `HMM-based synthesis of creaky voice', Interspeech 2013, Lyon, France. (Paper).
  • Ní Chasaide, A., Yanushevskaya, I., Kane, J., Gobl, C., (2013)
    `The Voice Prominence Hypothesis: the Interplay of F0 and Voice Source Features in Accentuation', Interspeech 2013, Lyon, France. (Paper).
  • Kane, J., Gobl, C., (2013)
    `Evaluation of automatic glottal source analysis', NOLISP 2013, Mons, Belgium. (Paper). (Slides).
  • Kane, J., Scherer, S., Aylett, M., Morency, L-P., Gobl, C., (2013)
    `Speaker and language independent voice quality classification applied to unlabelled corpora of expressive speech', ICASSP 2013, Vancouver, Canada. (Paper). (Poster).
  • Drugman, T., Kane, J., Raitio, T., Gobl, C., (2013)
    `Prediction of creaky voice from contextual factors', ICASSP 2013, Vancouver, Canada. (Paper). (Poster).
  • Drugman, T., Kane, J., Gobl, C., (2012)
    `Resonator-based creaky voice detection', Interspeech 2012, Portland, Oregon, USA.(Paper), (Poster),
  • Drugman, T., Kane, J., Gobl, C., (2012)
    `Modeling the creaky excitation for parametric speech synthesis', Interspeech 2012, Portland, Oregon, USA.(Paper). (Slides).
  • Székely, É, Kane, J., Scherer, S., Gobl, C., Carson-Berndsen, J., (2012)
    `Detecting a targetted voice style in an audiobook using voice quality features', in Proceedings of ICASSP 2012, Kyoto, Japan (Paper). (Poster).
  • Kane, J. and Gobl, C., (2011)
    `Identifying regions of non-modal phonation using features of the wavelet transform', in Proceedings of Interspeech 2011, Firenze, Italy (Paper).
  • Cabral, J., Kane, J., Gobl, C., and Carson-Berndsen, J., (2011)
    `Evaluation of glottal epoch detection algorithms on different voice types', in Proceedings of Interspeech 2011, Firenze, Italy (Paper).
  • Kane, J., Papay, K., Hunyadi, L., and Gobl, C., (2011)
    `On the use of creak in Hungarian spontaneous speech', in Proceedings of ICPhS 2011, Hong Kong (Paper).
  • Yanushevskaya, I., Kane, J., ,Gobl, C., Ní Chasaide, A. (2010). `An Exploration of Voice Source Correlates of Focus', in Proceedings of Interspeech 2010, Makuhari, Japan. (Paper)

Voice Quality Samples - Speech Communication Paper Submission

Toolkits

COVAREP - A collaborative voice analysis repository for speech technologies (Website) (GitHub)

Voice Analysis Toolkit (GitHub)


Curriculum Vitae

CV: (Link) Last updated 17th June 2013.

 

Back to top