Automatically-determined Unit Inventories for Unit Selection Text-to-Speech Synthesis
Lead Research Organisation:
University of Edinburgh
Department Name: Centre for Speech Tech Research-PPLS
Abstract
Speech synthesis - the generation of speech by computer - is a key technology for mobile computing and telephone-based services. A recent development, called Unit selection speech synthesis has now improved the quality of the speech so much that it is often indistinguishable from natural speech.Unfortunately, the creation of new voices for this unit selection technology is very expensive because it is labour intensive and must be done by experts. This is preventing the use of the technology in many applications, such as the production of high quality speech synthesisers for languages spoken in less developed countries.We are proposing to develop methods that will make it much quicker and cheaper to create new voices for speech synthesisers and also allow non-experts to carry out this work.
Organisations
Publications
M Aylett
(2009)
Speech synthesis without a phone inventory
in Interspeech
M Aylett And J Yamagishi
(2008)
Combining Statistical Parameteric Speech Synthesis and Unit-Selection for Automatic Voice Cloning
in Proc. LangTech 2008
M Aylett And S KIng
(2008)
Single Speaker Segmentation and Inventory Selection Using Dynamic Time Warping Self Organization and Joint Multigram Mapping
in SSW06
S King, K Tokuda, H Zen, J Tamagishi
(2008)
Unsupervised adaptation for HMM-based speech synthesis
in Proc. Interspeech
Description | The project succeeded in producing both statistical parametric and unit selection "emergent phone" systems. In addition we also created orthographic unit-based systems. These systems were evaluated against classical phone systems. A large number of techniques were evaluated for generating these systems and applied to the two main underlying problems that needed tobe solved namely:* Segmenting and categorising units of speech. * Generalising the expected units in unseen words from a database of s |
Description | Invited public lecture: A survey of speech technology |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | Discussions with the audience Follow up emails from members of the audience |
Year(s) Of Engagement Activity | 2009 |
Description | The future of Languages - more than just words |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Public/other audiences |
Results and Impact | A public lecture at the Public Library in Amsterdam, followed by a debate with an audience. Interactions with the audience. |
Year(s) Of Engagement Activity | 2012 |
URL | http://www.clubofamsterdam.com/event.asp?contentid=854 |