About CLST | uu77

Founded in January 2003, the Centre for Language and Speech Technology (CLST) stands as a proud institution dedicated to advancing the field of language and speech technology. Our mission is clear: to contribute to the development and progress of this exciting domain.

We actively engage in application development and provide expert consultancy services. Our passion lies in projects that bridge the gap between research and real-world applications, and we take great pride in our ability to make a tangible impact. Whenever possible, we share our groundbreaking projects in esteemed research journals, ensuring that our contributions reach a wide audience and inspire further innovation.

Collaborating with national and international research programs, as well as commercial partners, we embrace diverse opportunities to bring our expertise to the forefront. The Centre for Language and Speech Technology is here to make its mark, pushing boundaries and shaping the future of language and speech technology.

Mission, vision and Strengths

Mission & Vision

Mission

CLST aims at fundamental and applied research in the field of language and speech technology (LST). The focus is on the use and development of LST in the following research domains:

1. Multimedia mining (in written text and speech)
2. Language learning and language teaching
3. Communication in health care
4. Language resources and infrastructure

For this type of research CLST engages in collaborations with other academic institutions, commercial and non-profit organizations. CLST publishes its research findings in scientific and popularising articles. CLST also offers consultancy in each of the aforementioned domains.

Vision

Over the past decennia our society has developed into an information society in which increasingly more data is available, often in the form of text (spoken or written), for use on an individual basis or in aggregated form. The high degree of digitization has an enormous impact on our daily lives.

Therefore it is all the more important that no citizens find themselves excluded and to make sure that everyone – the elderly, the young, natives, non-natives, those highly educated, those lowly educated, people with communication disorders, etc. – can (continue to) participate in the information society.

Language and speech technology (LST) offers many opportunities in this respect and CLST envisages to play a prominent role, both nationally and internationally.

Our strengths

CLST focuses on fundamental and applied research in the field of Language and Speech Technology, in order to make sure that the citizens of today and tomorrow are able to continue to participate in our information society. Although our research is widely specialized in the field of Language and Speech Technology, our strength lies in the following points in particular.

Knowledge and expertise in speech technology, particularly in fundamental ASR technology and speech data
Knowledge and expertise in language technology, particularly in the integration of rule-based and statistical processing of written language
Combination of knowledge and expertise in the field of both language and speech technology
Combination of fundamental and applied research
Strongly embedded in the Digital Humanities context of the Faculty of Arts
A strong network of national and international contacts

CLARIN C Centre

As a CLARIN C Centre, we actively participate in the CLARIN (Common Language Resources and Technology Infrastructure) infrastructure. CLARIN is a European research infrastructure that aims to make language resources and technology more easily accessible for research and development in the humanities and social sciences. As a CLARIN C Centre we play a critical role in collecting, curating, and providing access to language resources and tools and their metadata. These resources encompass a wide range of data, including textual corpora, lexicons, annotations, audio recordings, and more. Our mission is facilitating access to language resources and technology for researchers in the humanities and social sciences. These resources empower researchers to delve deep into linguistic analysis, explore language variation, study language acquisition, and much more.

To enhance accessibility and interoperability, we support a diverse array of formats. Below we showcase the supported file formats for various types of language resources.

Supported file formats

Preferred metadata format for distribution through our CLARIN C Centre

CMDI - This format is explained here:

Preferred data formats for data distribution through ACE

ACE is the CLARIN Knowledge Centre for Atypical Communication Expertise (see ). Due to its collaboration with The Language Archive of the MPI for Psycholinguistics, ACE accepts all data formats listed here: .

Preferred input formats for our webservices

You will need to consult the webservice specification for webservices you intend to use, but in general, we have the following preferred input formats:

plain text (UTF-8 encoded) - (MIME: plain/text) - The most basic text format, does not offer further any further structural or mark-up semantics. Certain webservices may pose additional constraints, such as requiring one sentence or even one word per line (for e.g. a lexicon). Webservices may also attempt to automatically infer structure like paragraphs based on newlines. You should always use the UTF-8 (unicode) character encoding, other encodings are often not supported. UNIX line endings are usually preferred for most tools.
FoLiA XML - (MIME: application/folia+xml) - This is an XML-based format for linguistic annotation, developed in the scope of the CLARIN-NL, CLARIAH-CORE and CLARIAH-PLUS projects and used as a format for language resource exchange and corpus representation. It is widely used in the dutch & flemish NLP community and a lot of our NLP tools will either accept and/or produce FoLiA XML. See for more information about this format.
WAV - (MIME: audio/x-wav) - Most of our audio services accept this format, usually preferably 16/24 bit, 44.1/48 kHz, uncompressed PCM, 1 or 2 channels. Our audio services will likely also accept MP3 and OGG, but these come with quality loss due to compression.

Non-preferred input formats for our webservices

Microsoft Word/Excel/etc... - For both NLP as well as data storage purposes, proprietary word-processing formats such as Microsoft Word (doc/docx) are always discouraged. Alternatives such as Open Document Text (ODT) are preferred. Nevertheless, we offer a webservice (Piereling) which can attempt to convert such documents.
PDF - The use of PDF is ubiquitous but often very problematic as an *input* format for NLP purposes as it is hard to extract the textual information; other formats are preferred. It may be a valid source of input for OCR such as provided by our webservice PICCL. It is also a valid output format for presentational purposes.
HTML - Like PDF, HTML is suitable for output, but hardly ever makes a good input format.

Data Curation Service

The Data Curation Service (DCS) started in 2011 as a project of CLARIN-NL and will be continued in CLARIAH until 2024. The DCS is concerned with making collections of research data in the linguistic field accessible and is housed at the Centre for Language and Speech Technology (CLST) at uu77. The DCS aims to bridge the gap between researchers with interesting research material and the CLARIN-NL / CLARIAH data centres. We work together with researchers and experts. Our data curation specializes in (but is not limited to) datasets and corpora for atypical communication. CLST is also a separate knowledge centre () within CLARIN for this purpose.

More information

Information for researchers

One of the tasks of the DCS is to look for data that is interesting to curate. Researchers in the Humanities who have access to relevant data, in whatever format, are cordially invited to contact the staff of the DCS to find out what the options are for curation. This may concern texts, transcripts and media files such as video or sound recordings, to name a few. Data curation ensures permanent storage of the collected research data. Moreover, after storage in a CLARIN data centre the data will be available and searchable for other researchers and the data can thus be of additional value.

To contact the Data Curation Service, e-mail henk.vandenheuvel [at] ru.nl.

DCS employees

Project leader: Dr Nelleke Oostdijk
Coordinator: Dr Henk van den Heuvel
IT-specialists: Dr Maarten van Gompel, Dr Eric Sanders

Funder

DCS's funder is CLARIAH, the Dutch branch of CLARIN. In the context of CLARIAH, a digital research infrastructure is being built for the humanities.

Organisation

CLST is a unit within the Faculty of Arts of the uu77 Nijmegen and embedded in the Centre for Language Studies (CLS). It has a director and a board. Final responsibility is with the Dean of the Faculty.

Coordinator and Board

CLST Coordinator

The coordinator of CLST is Henk van den Heuvel.

CLST Advisory Board

CLST has an Advisory Board whose task it is to advise on CLST's policies and plans, and to monitor the progress in the realisation of these.

Nelleke Oostdijk (Chair), CLS, uu77
Tibor Bosse, Behavioural Science Institute, uu77
Martha Larson, CLS & Data Science, uu77

External members

, University of Twente
, Radboud UMC
, The Netherlands Institute for Sound & Vision
, Philips

Faculty-based Advisors

Enny Das, Director CLS, uu77
Nico Schröder, Faculty of Arts, uu77