SIG

ISCA Special Interest Group: Spoken Language Translation

Aims. The SIG SLT covers all aspects of spoken language translation ⁠— simultaneous translation and interpretation, speech dubbing, speech-to-text translation, speech-to-speech translation, cross-lingual communication including paralinguistic, emotional or multimodal information, and related areas ⁠ SIG SLT will (a) provide members of ISCA with a special interest in spoken language translation and its related areas with a means of exchanging news of recent research developments and other matters of interest in spoken language translation; (b) organize challenges and evaluation campaigns; (c) sponsor and organize the International Conference on Spoken Language Translation (IWSLT), meetings, satellites, and tutorial workshops in spoken language translation, operating within the framework of ISCA's by-laws for SIGs; and (d) make available open-source code and data resources, best practices and tools, and evaluation metrics relevant to spoken language translation.

Motivation. Recent interest in speech translation and simultaneous translation by machine has been growing explosively, due to continued performance advances and a growing international need for simultaneous translation and interpretation, speech dubbing, speech-to-text translation, speech-to-speech translation, cross-lingual communication including paralinguistic, emotional or multimodal information, and related areas. The under-covered elements in the current research are, for instance, incremental simultaneous speech-to-speech translation, paralinguistic translation, speaking style translation across languages. The proposed SIG will be organized by the members who are interested in spoken language translation/interpretation from various related areas such as ASR, TTS, and MT.

SIG SLT emerges from over two decades of organizing the International Conference on Spoken Language Translation (IWSLT) and its predecessor C-Star, scaling operations in response to significant growth in the field. The organizers of IWSLT and partners believe it is now time to join with ISCA by creating an ISCA SIG. IWSLT has a 15-year track record of profitability; it runs the premier benchmarking campaign on spoken language translation annually accompanied by an international scientific conference to present and discuss results.

Board. The officers for 2020-2021 are:

  1. Chair and ISCA liaison representative: This email address is being protected from spambots. You need JavaScript enabled to view it., Nara Institute of Science and Technology (NAIST), Japan (website)
  2. Secretary: This email address is being protected from spambots. You need JavaScript enabled to view it., Fondazione Bruno Kessler (FBK), Trento, Italy (website)

SIG-SLT News:

  • SIG-SLT Talk Series:   https://iwslt.org/lectures/

ISCA-supported event

  • (more to come)

Other events

  • International Workshops on Spoken Language Translation (IWSLT)
    • IWSLT 2020 Virtual, 9-10/7/2020
    • IWSLT 2019 Hong-Kong (China), 2-3/11/2019 (proceedings)
    • IWSLT 2018 Bruges (Belgium) 29-30/10/2018 (proceedings)
    • IWSLT 2017 Tokyo (Japan) 14-15/12/2017 (proceedings)
    • IWSLT 2016 Seattle (USA) 8-9/12/2016
    • IWSLT 2015 Da Nang (Vietnam), 3-4/12/2015
    • IWSLT 2014 Lake Tahoe (USA) 4-5,/12/2014 (proceedings)
    • IWSLT 2013 Heidelberg (Germany) 5-6/12/2013 (proceedings)
    • IWSLT 2012 Hong-Kong (China) 6-7/12/2012
    • IWSLT 2011 San Francisco (USA) 8-9/12/2011
    • IWSLT 2010, Maison de la Chimie- Paris (France), 2-3/12/2010
    • International Workshops on Spoken Language Translation (IWSLT):  https://iwslt.org/

Join the SIG: please contact This email address is being protected from spambots. You need JavaScript enabled to view it., Nara Institute of Science and Technology, Japan

ISCA Special Interest Group: Security and Privacy in Speech Communication (SPSC)

Click here to visit the SIG SPSC website!

Aims. The purpose of the SPSC is to promote research in those aspects of security and privacy which are related to speech communication; to provide a platform for communication for members of ISCA who are interested in security and privacy; to promote interdisciplinary research and collaboration also beyond ISCA, with areas such as user-interface design, study of the law, cryptography, and cognitive sciences.

Motivation. An increasing number of devices are connected to the Internet and feature a microphone. These devices can provide many useful services such as personal speech assistance and security monitoring. Moreover, automated speech interfaces are becoming more common in many services such as banking, call centres and medical services. This trend however exposes users to an increasing number of threats to their privacy and security. The growing amount of data increases the consequences of breaches, whereas the risk of a breach is increasing with the number of locations where data is processed and stored, the amount of data, the processing methods, storage formats and with whom the data is shared. Privacy and security is an interdisciplinary topic which ranges over all areas of ISCA, including among others, computer science, linguistics, phonetics, acoustics, cognitive sciences and medical sciences. To counter threats to security and privacy we therefore need collaboration across all areas of expertise within ISCA.
The analysis of security and privacy in speech communication, while aiming at transparency to non-experts in speech technology (e.g., system integrators, management, journalists, and the larger public), requires to develop taxonomies to interrelate research outcomes within a bigger picture. These taxonomies provide classification schemes and semantics to security and privacy in speech communication regarding, e.g.

  1. The information in speech which merits protection,
  2. Capture of speech signals,
  3. Processing of speech data,
  4. Storage of speech data,
  5. Entities in speech data life-cycles,
  6. User-interface design,
  7. Case studies and
  8. Technology safeguards.

In other words, SPSC will not only tackle safeguard technology but also will pursue to frame their context in a way useful to services and products in speech communication.

Board. The officers for 2019-2020 are:

  • Chair and ISCA liaison representative: This email address is being protected from spambots. You need JavaScript enabled to view it., Aalto University, Finland (website)
  • Secretary: This email address is being protected from spambots. You need JavaScript enabled to view it., Eurecom, Sophia Antipolis, France (website)

ISCA-supported event

Other events

Join the SIG: please contact This email address is being protected from spambots. You need JavaScript enabled to view it., Eurecom, Sophia Antipolis, France

ISCA Special Interest Group: Robust Speech Processing (RoSP)

Click here to visit the SIG website!

Aims. RoSP aims at providing the following services:

  • to promote interest in Robust Speech Processing;
  • to provide members of ISCA with a special interest in Robust Speech Processing with a means of exchanging news of recent research developments and other matters of interest in Robust Speech Processing;
  • to promote better understanding of the robustness challenges posed by real-world speech applications at various levels, including (but not limited to) the acoustic level (channel change, reverberation, background noise, overlapping speech...), the speaker level (stressed speech, Lombard speech, speaker change, change of speaking rate, accent...) and the language level (dialect, topic change...);
  • to facilitate the development of theoretical foundations and practical techniques addressing these challenges by means of shared goals and terminology;
  • to call attention to the applications of these techniques, including (but not limited to) automatic speech recognition, speaker identification and verification, spoken document retrieval, dialogue, speech-to-speech translation, speaker localization, speech separation, human-machine interfaces, robust training for synthesis;
  • to create a scientific link between researchers and others working in the various disciplines associated with Robust Speech Processing;
  • to provide and make available resources relevant to Robust Speech Processing, including speech and text corpora, best-practice processing and evaluation methodologies, processing and evaluation software, research papers and generated data;
  • to propose reviewers for ISCA conferences and workshops and to nominate outstanding members for ISCA awards;
  • and to sponsor meetings, workshops and evaluation campaigns in Robust Speech Processing that appear to be timely and worthwhile, operating within the framework of ISCA's by-laws for SIGs.

Motivation. Along with the rest of the speech processing community, robust speech processing has experimented strong changes in the last years. These changes have been driven by the maturity of fields like automatic speech recognition (ASR) which has been labeled an strategic asset by some of the biggest and more research-active players in the new technologies market. This maturity calls for new organizational forms that help the coordination within the community and allow it to adapt to this new dynamic scenario. The RoSP-SIG is born as a tool to help reaching this goal. Its aim is to strengthen the ties between the different sub-fields involving robust speech processing and coordinate actions in the interest of the community such as increasing resource availability, create guidelines or organize specific workshops.

Board. Current board members are:

  • Chair: This email address is being protected from spambots. You need JavaScript enabled to view it. (CMU, USA)
  • ISCA Liaison Officer: This email address is being protected from spambots. You need JavaScript enabled to view it. (NTT, Japan)

ISCA-supported events. RoSP supports the series of workshops on Hands-free Speech Communication and Microphone Arrays (HSCMA):

RoSP supports several events at major speech conferences:

To join, just register to our Google group

You are also welcome to join our LinkedIn group

ISCA Special Interest Group: Under-resourced Languages (SIGUL)

Aims. SIGUL intends to bring together a number of professionals involved in the development of language resources and technologies for under-resourced languages. Its main objective is to build a community that not only supports linguistic diversity through technology and ICT but also commits to increase the lesser-resourced languages (regional, minority, or endangered) chances to survive the digital world through language and speech technology. SIGUL is a joint Special Interest Group of the European Language Resources Association (ELRA) and of the International Speech Communication Association (ISCA).

Motivation. Porting a NLP system (for instance a speech recognition system or a syntactic parser) to a lesser-resourced language requires techniques that go far beyond the basic re-training of the models. Indeed, processing a new language often leads to new challenges (special phonetic and phonological systems, word segmentation problems, fuzzy grammatical structure, unwritten language, etc.). The lack of resources requires, on its side, innovative data collection methodologies (via community sourcing for instance) or models for which information is shared between languages (e.g. multilingual acoustic models) or even approaches that do not need annotated data (e.g. zero-resource or zero-shot methods). In addition, some social and cultural aspects related to the context of the targeted language bring additional problems: languages with many dialects in different regions, code-switching phenomena, massive presence of non-native speakers. It is also important to bridge the gap between language experts, native speakers and technology experts.  Finally, digital humanities offer new opportunities to work on ancient languages which are inherently under-resourced. Therefore, the main goal of this SIG will be to increase interaction between researchers interested in all the above topics.

Board.

  • Chair and ELRA liaison representative: This email address is being protected from spambots. You need JavaScript enabled to view it. (CNR-ILC, Pisa, Italy)
  • Co-chair and ISCA liaison representative: This email address is being protected from spambots. You need JavaScript enabled to view it. (LIG, Grenoble, France)
  • Secretary: This email address is being protected from spambots. You need JavaScript enabled to view it. (NAIST, Nara, Japan)
  • Contributor: Dorothee Beermann (NTNU, Norway)

ISCA-supported events

  • Spoken Language Technologies for Under-resourced Languages (LSTU) workshops
  • workshops at LREC
    • LREC 2014 (Reykjavik, Iceland) "Collaboration and Computing for Under Resourced Languages in the Linked Open Data Era", proceedings
    • LREC 2012 (Istanbul, Turkey) "Language technology for normalisation of less-resourced languages", proceedings
    • LREC 2010 (Malta) "Creation and use of basic lexical resources for less-resourced languages", proceedings
    • workshop at LREC 2008 (Marrakech, Morocco) "Collaboration: interoperability between people in the creation of language resources for less-resourced languages", proceedings
  • Other related events
    • CCURL 2018 (Miyazaki, Japan) "Collaboration and Computing for Under-Resourced Languages - Sustaining Knowledge Diversity in the Digital Age" web, proceedings
    • CCURL 2016 (Portoroz, Slovenia) "Collaboration and Computing for Under-Resourced Languages - Towards an Alliance for Digital Language Diversity" proceedings
    • CCURL 2014 (Reykjawik, Iceland) "Collaboration and Computing for Under-Resourced Languages in the Linked Open Data Era" proceedings

Join the SIG: please contact This email address is being protected from spambots. You need JavaScript enabled to view it. (LIG, Grenoble, France)
More information on SIGUL can be found here

ISCA Special Interest Group: Russian Speech Analysis (SIG-RU)

Click here to visit the SIG website!

Aims. SIGRU has the overall aim of promoting research and development in the scientific, technical, professional and didactic fields of speech and language technology for Russian speech analysis, particularly formal methods of analysis. SIGRU will pursue its own purposes in particular:

  • promote and organize conferences, schools and workshops;
  • announce publications (papers, theses and dissertations) on topics related to Russian speech analysis and/or by authors that are members of this SIG;
  • promote industry / university collaboration;
  • promote interdisciplinary scientific communication of researchers dealing with speech analysis;
  • promoting scientific and technical exchange of information and relationships of collaboration between the associates;
  • promoting electronic discussion through the Internet (Web site, discussion list, etc).
  • maintaining a database of active researchers.
  • providing a channel of communication between Russian speech researchers and those active in speech and language technology in general.

Motivation. The SIG promotes research activities in Russian speech analysis. Its main focus is the use of formal representations of the sound system of Russian in order to enable automatic processing of large speech corpora and automatically interpret speech events in terms of phonetic/linguistic phenomena.

Board. Current SIG officers are:

  • Chairperson: Dr. Pavel Skrelin (St.-Petersburg State University, Russia)
  • Secretary and ISCA Liaison Officer: Daniil Kocharov (St.-Petersburg State University, Russia)

ISCA-supported events

  • XXXVII International Philological Conference 2008, 11/3-15/3, Saint-Petersburg, Russia

Join the SIG

More Articles ...

  1. ISCA Special Interest Group: Indian Speech & Language Processing (ILSP)
  2. ISCA Special Interest Group: Iberian Languages (IL-SIG)
  3. ISCA Special Interest Group: Italian Association for Speech Science (AISV)
  4. ISCA Special Interest Group: French-speaking Speech Communication Association (AFCP)
Copyright @ 2009 - 2023 International Speech Communication Association    -