Odyssey 2020

The Speaker and Language Recognition Workshop

Announcement [Nov 14, 2020]: The Odyssey 2020 best paper award was announced during the Closing and Award Ceremony. Congratulations to all the authors, and many thanks to our Best Paper Award Committee and reviewers for their wonderful contribution.

Best Paper Award

Daniel Garcia-Romero, Greg Sell, and Alan McCree, "MagNetO: X-vector Magnitude Estimation Network plus Offset for Improved Speaker Recognition"


  • Shaoshi Ling, Julian Salazar, Yuzong Liu, and Katrin Kirchhoff, “BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"
  • Qiongqiong Wang, Kong Aik Lee, and Takafumi Koshinaka, "Using Multi-Resolution Feature Maps with Convolutional Neural Networks for Anti-Spoofing in ASV"

Announcement [Nov 14, 2020]: Congratulations to the recipients of the inaugural Jack Godfrey's Best Student Paper Award

Anna Silnova, Niko Brummer, Johan Rohdin, Themos Stafylakis, and Lukas Burget, “Probabilistic Embeddings for Speaker Diarization"


  • Nikolaos Flemotomos, Panayiotis Georgiou, and Shrikanth Narayanan, “Linguistically Aided Speaker Diarization Using Speaker Role Information"
  • Zhongxin Bai, Xiao-Lei Zhang, and Jingdong Chen, “Partial AUC Metric Learning Based Speaker Verification Back-End"
  • Shreyas Ramoji, Prashant Krishnan, and Sriram Ganapathy, “NPLDA: A Deep Neural PLDA Model for Speaker Verification"

Announcement [Nov 01, 2020]: We have a Slack workspace "Odyssey2020virtual" for help and general discussion. Click here to join.

Announcement [Oct 29, 2020]: We are excited to bring together a community of more than 300 people to the Odyssey 2020 Virtual Workshop. The program is now available here.

Announcement [Aug 30, 2020]: To expand our reach and serve our community with resources during this time, Odyssey 2020 is now free for non-author / non-covering author regsitration. Register for Odyssey 2020 Workshop here. [Oct 09, Registration has been closed]

Announcement [July 31, 2020]: The safety and well-being of our authors and participants are of paramount importance. After careful consideration and in light of the global travel restrictions, the Steering Committee of Odyssey 2020 has decided to convert Odyssey 2020 to a fully virtual workshop. New information will be published on the website soon.

Announcement [May 18, 2020]: The proceedings of Odyssey 2020 are now available on ISCA Archive: https://www.isca-speech.org/archive/Odyssey_2020/

Announcement [March 27, 2020]: Given COVID-19 situation worldwide, we decided to postpone the Odyssey workshop to Nov 01 to 05, 2020. The location remains the same in Tokyo. The workshop proceedings will be published (ISCA Archive) on May 18, 2020, for all papers registered before April 30, 2020.

Odyssey 2020 in Tokyo
The Speaker and Language Recognition Workshop

Odyssey 2020: The Speaker and Language Recognition Workshop will be hosted by NEC Corporation and Tokyo Institute of Technology in Tokyo, Japan, on Nov 02-05, 2020. The workshop is an ISCA tutorial and research workshop held in cooperation with the ISCA Speaker and Language Characterization special interest group. For the first time, Odyssey 2020 will feature a tutorial day on Nov 01, 2020, before the Odyssey 2020 workshop. The tutorial day would further strengthen the Odyssey 2020 as an ISCA Tutorial and Research Workshop (ITRW).

The need for fast, efficient, accurate, and robust means of recognizing people and languages is of growing importance for commercial, forensic, and government applications. The aim of this workshop is to continue to foster interactions among researchers in speaker and language recognition as the successor of previous successful events held in Martigny (1994), Avignon (1998), Crete (2001), Toledo (2004), San Juan (2006), Stellenbosch (2008), Brno (2010), Singapore (2012), Joensuu (2014), Bilbao (2016) and Les Sables d’Olonne (2018).

The general topics of the workshop are speaker and language characterization and recognition. The specific topics include, but are not limited to, the following:

  • Speaker and language recognition, verification, and identification
  • Speaker and language characterization
  • Features for speaker and language recognition
  • Speaker and language clustering
  • Multispeaker segmentation, detection, and diarization
  • Language, dialect, and accent recognition
  • Robustness in channels and environment
  • System calibration and fusion
  • Speaker recognition with speech recognition
  • Multimodal speaker recognition
  • Speaker recognition in multimedia content
  • Machine learning for speaker and language recognition
  • Confidence estimation for speaker and language recognition
  • Corpora and tools for system development and evaluation
  • Low-resource (lightly supervised) speaker and language recognition
  • Speaker synthesis and transformation
  • Human and human-assisted recognition of speaker and language
  • Spoofing/presentation attacks: analysis and countermeasures
  • Forensic and investigative speaker recognition
  • Systems and applications


20 November 2019
Paper submission opens
20 27 January 2020
Regular paper submission deadline
27 January 01 February 2020
Regular paper modification deadline
16 25 March 2020
Notification of acceptance
08 April 2020
Final paper due
18 May 2020
Preliminary program / Proceedings Available on ISCA Archive
01 Nov 2020
Tutorial day
02 – 05 Nov 2020