Show simple item record

Depositordc.contributorRichmond, Korin
Funderdc.contributor.otherEPSRC - Engineering and Physical Sciences Research Councilen_UK
Data Creatordc.creatorRichmond, Korin
Data Creatordc.creatorKing, Simon
Date Accessioneddc.date.accessioned2016-01-19T16:51:57Z
Date Availabledc.date.available2016-01-19T16:51:57Z
Citationdc.identifier.citationRichmond, Korin; King, Simon. (2016). Listening test materials for "Smooth Talking: Articulatory Join Costs for Unit Selection", [dataset]. https://doi.org/10.7488/ds/1315.en
Persistent Identifierdc.identifier.urihttp://hdl.handle.net/10283/1891
Persistent Identifierdc.identifier.urihttps://doi.org/10.7488/ds/1315
Dataset Description (abstract)dc.description.abstractThis is the listening test data for the experiment presented in the ICASSP 2016 paper "Smooth Talking: Articulatory Join Costs for Unit Selection", which proposes and evaluates computation of unit selection join costs in the articulatory domain. Join cost calculation has so far dealt exclusively with acoustic speech parameters, and a large number of distance metrics have previously been tested in conjunction with a wide variety of acoustic parameterisations. In contrast, we propose here to calculate distance in articulatory space. The motivation for this is simple: physical constraints mean a human talker's mouth cannot ``jump'' from one configuration to a different one, so smooth evolution of articulator positions would also seem desirable for a good candidate unit sequence. To test this, we built Festival Multisyn voices using a large articulatory-acoustic dataset. We first synthesised 460 TIMIT sentences and confirmed our articulatory join cost gives appreciably different unit sequences compared to the standard Multisyn acoustic join cost. A listening test (3 sets of 25 sentence pairs, 30 listeners) then showed our articulatory cost is preferred at a rate of 58% compared to the standard Multisyn acoustic join cost.en_UK
Dataset Description (TOC)dc.description.tableofcontents./README => short description of dataset ./stimuli/ => utterances (used in listening test) synthesised by 3 unit selection voices ./responses/ => listener responses for 3 preference testsen_UK
Languagedc.language.isoengen_UK
Rightsdc.rightsCreative Commons Attribution 4.0 International Public Licenseen
Subjectdc.subjectspeech synthesisen_UK
Subjectdc.subjectunit selectionen_UK
Subjectdc.subjectlistening testen_UK
Subjectdc.subjectarticulationen_UK
Subject Classificationdc.subject.classificationTechnologiesen_UK
Titledc.titleListening test materials for "Smooth Talking: Articulatory Join Costs for Unit Selection"en_UK
Typedc.typedataseten_UK
Publisherdcterms.publisher

Download All
zip file MD5 Checksum: 5e264194669cbf2e5bd921121d8dcc4c

Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record