{"id":8033,"date":"2017-05-23T07:17:13","date_gmt":"2017-05-23T05:17:13","guid":{"rendered":"https:\/\/www.uni.lu\/c2dh-en\/articles\/catching-speech-in-arezzo-a-clarin-workshop-for-developing-a-transcription-chain-for-oral-history\/"},"modified":"2025-03-26T10:12:55","modified_gmt":"2025-03-26T09:12:55","slug":"catching-speech-in-arezzo-a-clarin-workshop-for-developing-a-transcription-chain-for-oral-history","status":"publish","type":"articles","link":"https:\/\/www.uni.lu\/c2dh-en\/articles\/catching-speech-in-arezzo-a-clarin-workshop-for-developing-a-transcription-chain-for-oral-history\/","title":{"rendered":"Catching Speech in Arezzo: A Clarin workshop for developing a transcription-chain for Oral History"},"content":{"rendered":"\n
\n\n

The challenge of this workshop on 'transcription and technology\u2019, which took place from 10 to 12 May in Arezzo, consisted in turning recorded human speech into a textual representation that is as close as possible to what has been uttered. <\/strong><\/p>\n\n

Say Arezzo<\/strong> and any art historian\u2019s thoughts will divert to Piero della Francesca\u2019s<\/strong> innovation in the visual representation of reality. It was this renaissance painter of the 15th<\/sup> century who in his frescos dared to depicture religious figures as real humans. By creating the illusion of depth and light and by paying detailed attention to the anatomy of their bodies, Christ, the Madonna and other holy personalities were no longer spiritual creatures floating in the air, but looked like real people<\/a>.<\/p>\n\n

The efforts of a workshop on ‘transcription and technology\u2019, which we attended from 10 to 12 May in this beautiful Tuscan town, were also geared towards an accurate representation of reality. This time the challenge was turning recorded human speech into a textual representation that is as close as possible to what has been uttered. Speech retrieval technology can be relevant for humanities research in two ways: it can open up huge amounts of spoken data in archives of which the content is mostly unknown, and it can speed up the lengthy process of manual transcription for scholars who want to analyze their interviews in depth.<\/p>\n\n

The importance of studying speech is evident when taking into consideration the role of recorded voice and moving image for the human expression of the 20th century. Digital tools have already conquered the world of text, magnifying the scale and speed at which phenomena can be observed, but too little attention is given to how we use spoken language and memory to shape our lived experiences into a set of meaningful and coherent stories.<\/p>\n\n

With this agenda in mind, a mix of Italian, Dutch, British, Czech and German oral historians, linguists, data specialists and speech technologists got together to assess which Digitization,<\/em> Speech Retrieval<\/em>, Alignment<\/em> and Transcription<\/em> tools are suitable for creating a semi-automated workflow that can turn analogue recordings into readable transcripts. The workshop was supported by CLARIN ERIC<\/a>, a European infrastructure offering digital data and tools for Digital Humanities scholarly research. It was created to serve a broad range of scholars, but until recently it was foremost a much cherished treasure trove for linguists. The increased interest for cross-disciplinary approaches to data is the appropriate context for making efforts to recruit more enthusiastic users from the humanities and social science fields. This objective begs the question of which requirements are relevant to which type of scholar who works with speech data. It also asks scholars to step out of their ‘comfort zone’ and consider other approaches.<\/p>\n\n

Contributors were asked to present an overview of conventions and practices that should be considered to create a well suited workflow: What are the metadata schemes used in speech data? What are the guidelines for transcription? What are existing digital infrastructures capable of providing? And what has proprietary commercial software already have in store? After the technical partners presented a parade of tools, the real fun part started: testing the various tools with 5 minutes clips of audio. The speech retrieval tools are of course language-specific. For English they could try out the web service offered by Sheffield University: http:\/\/www.webasr.org\/<\/a> . The Dutch could try out https:\/\/webservices-lst.science.ru.nl\/oral_history\/<\/a> from the Radboud University in Nijmegen, and the Italians could practice with the stand-alone alignment software \u2018Segmenta\u2019<\/strong> created by Piero Cosi at the CNR in Padua. As expected, the speech retrieval software performed poorly with clips containing language with strong regional accents, such as a corpus with Tuscan dialect, or an interview with a narrator speaking with a Flemish\/Moroccan accent. The good news is however, that it performed excellently with language clips that contained regular speech, and that this applied to all three languages.<\/p>\n\n\n

\n
\n \n
\n
\n
\n