Retrieving Text from Spoken Data

Description
This video features speech technologist Henk van den Heuvel, linguist Silvia Calamai and data Louise Corti explaining how speech technology has reached the stage of being able to automatically recognise and retrieve speech in huge amounts of audio visual data.
Author(s)
  • Dr., van den Heuvel, Henk, Radboud University Nijmegen
    • Bionote: Henk studied German Language and Literature (main topic phonetics) in Utrecht. In 1996 he defended his PhD thesis entitled ’Speaker variability in acoustic properties of Dutch phoneme realisations’. He co-ordinated the work on orthographic transcriptions in various projects for KPN, Philips, Temic, and CGN. Since 2003 he is director of the Centre for Language and Speech Technology (CLST) at the Radboud University in Nijmegen, and since 2016 also head of the Humanities Lab. For CLST he was involved in various projects on resources and technology that are needed to improve automatic speech recognition and automatic name recognition.
  • Dr., Calamai, Silvia, University of Siena, Italy
    • Bionote: Silvia graduated in 1997 in Humanities at Florence University and received a PhD in Romance Philology and General Linguistics from Perugia University. She is currently the Associate Professor of Linguistics at Deparment of Education, Humanities and Intercultural Communication, Siena University. Her main research interests are experimental phonetics, sociolinguistics, sound archives and dialectology. She is in the board of Italian Association of Speech Sciences and of Sonorités Bulletin de l’AFAS Association française des détenteurs de documents audiovisuels et sonores. She cocoordinated the PAR-FAS Project on Oral Archives and Intangible Cultural Heritage Grammofoni (Gra.fo) “Le soffitte della voce”. In addition to over 100 scholarly contributions and two manuals for university students, she has written four books based on phonetic and dialectological fieldwork.
  • Dr., Corti, Louise, University of Essex
    • Bionote: Louise is an Associate Director and heads the UK Data Service functional areas of Collections Development and Producer Relations. The Collections Development team work to ensure that the most useful data are acquired and made available via the Service, using robust appraisal criteria. The Producer Relations arm works with data producers to ensure that high quality data are created and that grant applicants and award holders gain good advice on creating shareable data. Louise directs qualitative data activities at the UK Data Service and coordinates the international DDI working group on metadata standards for qualitative data. She is PI on a UK - South Africa Centre partnership project which is working with DataFirst at Cape Town University to explore creating large scale data infrastructure for policy and planning.
Contributor(s)
  • Dr., Scagliola, Stefania - C2DH, Luxebourg Centre for Contemporary and Digital History, Concept, Production and Metadata
  • Dr., van Hessen, Arjan - CLARIAH, University of Utrecht, Editing video, Speech recognition output, Subtitles and Metadata,
  • Mr., Wessels, Leon MA - CLARIN ERIC, Utrecht University, Recording, Sound
  • Miss., Greene, Sinéad - An Foras Feasa, Maynooth University, Metadata       
Date & Place
  • Date of Recording: 11th June 2017
  • Place of Recording: Arezzo, Italy, Clarin Workshop: Developing a Transcription Chain.
  • Publication: 12th December 2017, https://www.youtube.com/watch?v=5fskmqgcvtw
Audience
  • Undergraduates; Postgraduates; Scholars in Humanities, Information Science and Media Studies
  • Lecturers; Teachers 
  • Cultural Heritage Specialists; Digital Humanists; Speech Technologists, Oral Historians, Linguists, Sounds Studies, Phonologists; Media Studies, Librarians; Media Professionals; Museum Professionals
Language Information
  • Language Main: English
  • Language Transcription: Yes
  • Language Subtitles: Yes
NeDiMAH Methods Ontology (NeMO)
  • 2. Communicating > 2.1.5. Crowdsourcing > 2.1.7. Interviewing
  • 4. Processing > 4.1. Analysing > 4.1.10. Data Recognition > 4.2.18. Sequence Allignment
  • 4. Processing > 4.2. Modifying > 4.2.5. Conversioning > 4.2.7. Digitising > 4.2.11. Enriching
  • 4. Processing > 4.3. Organising > 4.3.1. Adding Meta Information > 4.3.2. Aligning
  • 4. Processing > 4.4. Preserving > 4.4.1. Curating
  • 5. Seeking > 5.7. Retrieving
  • 2. Computer files > 2.11. Sound
  • 7. Visual Material > 7.19. Video Recording
Keywords
  • Speech Technology; Oral History; Sound Recordings; Dialectology; Language Studies; Transcription; Crowdsourcing; Digital Technologies; Digital Humanities
References
  • Heuvel, H. van den, Sanders, E.P., Rutten, Robin, Scagliola, S., Witkamp, P. "An Oral History Annotation Tool for INTER-VIEWs." Proceedings of LREC 2012 2012, 215-218. Web.

  • Bertinetto, P.M., Calamai, S., Ginouvès, V. ”Digital audio archives accessibility.” Cultural Heritage in a Changing World. Ed. K.J. Borowiecki, N. Forbes and A. Fresa. SpringerOpen. 2016, 37-54.

  • Corti, L., Fielding, N.F. and Bishop, L. "Editorial for Special Edition, Digital Representations: Re-Using and Publishing Digital Qualitative Data." SAGE Open. 2016. Web.

  • Corti, L. ”Opportunities From the Digital Revolution, Implications for Researching, Publishing, and Consuming Qualitative Research.” SAGE Open 2016. Web.

Copyright Clearances
The video on this page has been cleared for any copyright material. #dariahTeach will accept no liability for any video that includes copyright protected content, including but not limited to images, sounds, and music. It is the sole responsibility of the 'Author(s)' named under the Author(s) category above to ensure that there is no copyright infringement.
Creative Commons
  • Any video published on #dariahTeach YouTube Channel is covered by a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
    Based on CC BY-NC-SA 4.0 license, anybody could 'Share’ — copy and redistribute the material in any medium or format
    Based on CC BY-NC-SA 4.0 license, anybody could ‘Adapt’ — remix, transform, and build upon the material.

    Attribution: You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
    NonCommercial — You may not use the material for commercial purposes.
    ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.

    More details on the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License can be found at: https//creativecommons.org/licenses/by-nc-sa/4.0/legalcode

Last modified: Wednesday, 20 December 2017, 12:24 PM