Publications by Sebastian Andersson

janderss.bib

@inproceedings{anderssonetal2010,
  author = {Andersson, Sebastian and Georgila, Kallirroi and Traum, David and Aylett, Matthew and Clark, Robert},
  title = {Prediction and Realisation of Conversational Characteristics by Utilising Spontaneous Speech for Unit Selection},
  booktitle = {Speech Prosody 2010},
  month = {May},
  year = {2010},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/100116.pdf},
  abstract = {Unit selection speech synthesis has reached high levels of naturalness and intelligibility for neutral read aloud speech. However, synthetic speech generated using neutral read aloud data lacks all the attitude, intention and spontaneity associated with everyday conversations. Unit selection is heavily data dependent and thus in order to simulate human conversational speech, or create synthetic voices for believable virtual characters, we need to utilise speech data with examples of how people talk rather than how people read. In this paper we included carefully selected utterances from spontaneous conversational speech in a unit selection voice. Using this voice and by automatically predicting type and placement of lexical fillers and filled pauses we can synthesise utterances with conversational characteristics. A perceptual listening test showed that it is possible to make synthetic speech sound more conversational without degrading naturalness.},
  categories = {speech synthesis, unit selection, conversation, spontaneous speech, lexical fillers, filled pauses}
}

@article{Andersson2012175,
  author = {Andersson, Sebastian and Yamagishi, Junichi and Clark, Robert A.J.},
  note = {},
  doi = {10.1016/j.specom.2011.08.001},
  title = {Synthesis and evaluation of conversational characteristics in {HMM}-based speech synthesis},
  url = {http://www.sciencedirect.com/science/article/pii/S0167639311001178},
  journal = {Speech Communication},
  issn = {0167-6393},
  number = {2},
  abstract = {Spontaneous conversational speech has many characteristics that are currently not modelled well by HMM-based speech synthesis and in order to build synthetic voices that can give an impression of someone partaking in a conversation, we need to utilise data that exhibits more of the speech phenomena associated with conversations than the more generally used carefully read aloud sentences. In this paper we show that synthetic voices built with HMM-based speech synthesis techniques from conversational speech data, preserved segmental and prosodic characteristics of frequent conversational speech phenomena. An analysis of an evaluation investigating the perception of quality and speaking style of HMM-based voices confirms that speech with conversational characteristics are instrumental for listeners to perceive successful integration of conversational speech phenomena in synthetic speech. The achieved synthetic speech quality provides an encouraging start for the continued use of conversational speech in HMM-based speech synthesis.},
  volume = {54},
  year = {2012},
  keywords = {Speech synthesis, HMM, Conversation, Spontaneous speech, Filled pauses, Discourse marker},
  pages = {175--188}
}

@article{anderssonyamagishi12,
  author = {Andersson, S. and Yamagishi, J. and Clark, R.A.J.},
  doi = {10.1016/j.specom.2011.08.001},
  title = {Synthesis and Evaluation of Conversational Characteristics in {HMM}-Based Speech Synthesis},
  journal = {Speech Communication},
  number = {2},
  abstract = {Spontaneous conversational speech has many characteristics that are currently not modelled well by HMM-based speech synthesis and in order to build synthetic voices that can give an impression of someone partaking in a conversation, we need to utilise data that exhibits more of the speech phenomena associated with conversations than the more generally used carefully read aloud sentences. In this paper we show that synthetic voices built with HMM-based speech synthesis techniques from conversational speech data, preserved segmental and prosodic characteristics of frequent conversational speech phenomena. An analysis of an evaluation investigating the perception of quality and speaking style of HMM-based voices confirms that speech with conversational characteristics are instrumental for listeners to perceive successful integration of conversational speech phenomena in synthetic speech. The achieved synthetic speech quality provides an encouraging start for the continued use of conversational speech in HMM-based speech synthesis.},
  volume = {54},
  year = {2012},
  pages = {175-188}
}

@inproceedings{anderssonetal2010_ssw7,
  author = {Andersson, Sebastian and Yamagishi, Junichi and Clark, Robert},
  title = {Utilising Spontaneous Conversational Speech in {HMM}-Based Speech Synthesis},
  booktitle = {The 7th ISCA Tutorial and Research Workshop on Speech Synthesis},
  month = {September},
  year = {2010},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/ssw7_paper.pdf},
  abstract = {Spontaneous conversational speech has many characteristics that are currently not well modelled in unit selection and HMM-based speech synthesis. But in order to build synthetic voices more suitable for interaction we need data that exhibits more conversational characteristics than the generally used read aloud sentences. In this paper we will show how carefully selected utterances from a spontaneous conversation was instrumental for building an HMM-based synthetic voices with more natural sounding conversational characteristics than a voice based on carefully read aloud sentences. We also investigated a style blending technique as a solution to the inherent problem of phonetic coverage in spontaneous speech data. But the lack of an appropriate representation of spontaneous speech phenomena probably contributed to results showing that we could not yet compete with the speech quality achieved for grammatical sentences.},
  categories = {HMM, speech synthesis, spontaneous speech, conversation, lexical fillers, filled pauses}
}