An Edinburgh Speech Production Facility

Lead Research Organisation: University of Edinburgh
Department Name: Sch of Philosophy Psychology & Language

Abstract

The proposal is for a facility designed to record and analyse the movements of the lips, tongue, and jaw during spoken dialogue. This facility will be the first of its kind in the UK, and will be useful for applications in speech recognition and speech synthesis, as well as for developing theories of the cognitive representations and processes involved in normal and impaired speech production. The first output of the facility will be a database of recorded dialogue that will be useful for researchers interested in the relationships between speech movement and acoustics (important for speech technology applications), as well as in the particular types of pronunciations that speakers use during spontaneous dialogue.

Publications


10 25 50
Felps D (2012) Foreign Accent Conversion Through Concatenative Synthesis in the Articulatory Domain in IEEE Transactions on Audio, Speech, and Language Processing
Geng, C., Mooshammer, C., Nam, H., Hoole, P. (2010) Between the Regular and the Particular in Speech and Language
Scobbie, JM (2011) A common co-ordinate system for mid-sagittal articulatory measurement in QMU CASL Working papers
Turk A (2014) Timing in talking: what is it used for, and how is it controlled? in Philosophical transactions of the Royal Society of London. Series B, Biological sciences
 
Description We created a publicly available corpus of speech recordings that includes synchronized articulatory and acoustic records of speech in dialogue. Our facility is available for funded use; we offer calibration, gluing, recording, and data post-processing services. We commissioned the development of data analysis software, available through Articulate Instruments.
URL http://www.lel.ed.ac.uk/projects/ema/
 
Title Double Electromagnetic Articulometry at the Edinburgh Speech Production Facility 
Description The Edinburgh Speech Production is unique worldwide in its capability of synchronously recording speech movement and acoustic data simultaneously from two participants in dialogue. This facility is built around two Carstens' AG500 electromagnetic articulographs, and acoustic recording equipment. The articulographs record the movements of sensors attached to the lips, tongue, jaw, and head at a sampling rate sufficiently high to obtain precise timing data about these movements (200 Hz). The facility is new; EPSRC funded its development from 2007-2010. As part of the EPSRC project, a U. of Edinburgh/ Queen Margaret University team recorded a corpus of 8 dialogue sessions. The dialogue corpus has been partially annotated, and will be available to the research community in 2010. We anticipate that it will be exploited for many purposes: For example, by speech technologists interested in the relationship between articulation and acoustics, and by linguists and psycholinguists interested in the relationship between grammar, pragmatics, and speech in an interactive 
Type Of Material Improvements to research infrastructure 
Provided To Others? No  
Impact The Edinburgh Speech Production Facility DoubleTalk corpus which is publicly available. 
URL http://www.ppls.ed.ac.uk/staff/resources/articulography.php
 
Title The Edinburgh Speech Production Facility DoubleTalk Corpus 
Description The DoubleTalk articulatory speech corpus includes synchronised audio and articulatory trajectories for 12 speakers of English. The corpus was collected at the Edinburgh Speech Production Facility (ESPF) using two synchronized Carstens AG500 electromagnetic articulometers. The first release of the corpus comprises orthographic transcriptions aligned at phrasal level to EMA and audio data for each of 6 mixed-dialect speaker pairs. It is available from the ESPF online archive (http://espf.ppls.ed.ac.uk/frontend.php/project/espf-doubletalk). A variety of tasks were used to elicit a wide range of speech styles, including monologue (a modified Comma Gets a Cure and spontaneous story-telling), structured spontaneous dialogue (Map Task and Diapix), a wordlist task, a memory-recall task, and a shadowing task. 
Type Of Material Database/Collection of data 
Year Produced 2010 
Provided To Others? Yes  
Impact This is the first corpus of its kind that is publicly available to researchers wishing to study the nature of speech articulation in spontaneous dialogue. 
URL http://espf.ppls.ed.ac.uk/frontend.php/project/espf-doubletalk
 
Description Queen Margaret University 
Organisation Queen Margaret University Edinburgh
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution Joint collaboration on our EPSRC An Edinburgh Speech Production Facility project (EP/E016359/1 to QMU; EP/E01609X/1 to U. of Edinburgh)
Collaborator Contribution Joint collaboration on our EPSRC An Edinburgh Speech Production Facility project (EP/E016359/1 to QMU; EP/E01609X/1 to U. of Edinburgh)
Impact Geng et al. 2013 Scobbie et al. 2013
Start Year 2007
 
Title AAA software: EMA component 
Description To enable wider use of EMA data from the ESPF facility, Articulate Instruments Ltd produced an extra component of the AAA software programme specifically to handle EMA data. This commerically-available software, designed for articulatory speech analysis, therefore provides the opportunity for users familiar with other articulatory data to access and analyse EMA data without having to learn new software. In addition, the company's contribution to the design of the facility enables synchronised collection of EPG (electropalatography) data. 
Type Of Technology Software 
Year Produced 2010 
Impact Sales of software, contributing to the economic success of the company (cf. REF Impact case study at QMU). 
URL http://www.articulateinstruments.com/