• Publications
  • Influence
Multisyn: Open-domain unit selection for the Festival speech synthesis system
TLDR
We present the implementation and evaluation of an open-domain unit selection speech synthesis engine designed to be flexible enough to encourage further unit selection research and allow rapid voice development by users with minimal speech synthesis knowledge. Expand
  • 156
  • 15
  • PDF
Festival 2 - build your own general purpose unit selection speech synthesiser
TLDR
This paper describes version 2 of the Festival speech synthesis system. Expand
  • 113
  • 9
  • PDF
The Blizzard Challenge 2008
The Blizzard Challenge 2008 was the fourth annual Blizzard Challenge. This year, participants were asked to build two voices from a UK English corpus and one voice from a Man- darin Chinese corpus.Expand
  • 134
  • 7
  • PDF
On generating combilex pronunciations via morphological analysis
TLDR
This paper explores one of these: the ability to generate fully-specified transcriptions for morphologically derived words automatically. Expand
  • 49
  • 6
  • PDF
Robust LTS rules with the Combilex speech technology lexicon
TLDR
Combilex is a high quality pronunciation lexicon, aimed at speech technology applications, that has recently been released by CSTR. Expand
  • 49
  • 6
  • PDF
Behavioural and cognitive influences of kairomones on an araneophagic jumping spider
In laboratory experiments, Portia fimbriata, an araneophagic salticid from Queensland, was influenced by olfactory and contact-chemical cues from Jacksonoides queenslandicus, an abundant salticid onExpand
  • 46
  • 5
Statistical analysis of the Blizzard Challenge 2007 listening test results
Blizzard 2007 is the third Blizzard Challenge, in which participants build voices from a common dataset. A large listening test is conducted which allows comparison of systems in terms of naturalnessExpand
  • 89
  • 4
  • PDF
Synthesis and evaluation of conversational characteristics in HMM-based speech synthesis
TLDR
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. Expand
  • 24
  • 4
  • PDF
Unsupervised and lightly-supervised learning for rapid construction of TTS systems in multiple languages from 'found' data: evaluation and analysis
TLDR
This paper presents techniques for building text-to-speech frontends in a way that avoids the need for language-specific expert knowledge, but instead relies on universal resources (such as the Unicode character database) and unsupervised learning from unannotated data to ease system development. Expand
  • 27
  • 4
  • PDF
Listeners' weighting of acoustic cues to synthetic speech naturalness: A multidimensional scaling analysis
TLDR
The quality of current commercial speech synthesis systems is now so high that system improvements are being made at subtle sub- and supra-segmental levels. Expand
  • 33
  • 3
  • PDF