Special Event Descriptions

 

Special events are unique sessions that may have invited speakers/panelists presenting or demonstrations taking place during the session. Please review the list below for more information regarding the special events taking place at Interspeech 2016.

 

MINDFULNESS SPECIAL EVENT

Saturday, 10 September | 08:00 - 08:25 | Grand Ballroom ABC

 

  1. Names and affiliation of organizers:
  • Nikki Mirghafori, International Computer Science Institute (ICSI), USA

 

  1. Short Description:

Mindfulness has entered the cultural mainstream in recent years, with classes and workshops offered on the topic at many universities and companies (including Google, Facebook, etc.). Mindfulness can be thought of as a way to train our mind to be fully present with this moment's experience with curiosity, kindness, and equanimity. The training can serve as a refuge in our busy professional lives and help build resilience. This special event will be in the form of a guided meditation and serve as an introduction for those who are new to this practice, and a chance to practice in community for those who have previous experience. Everyone is welcome.

 

Clinical and neuroscience-inspired vocal biomarkers of neurological and psychiatric disorders

Saturday, 10 September | 10:00 - 12:00 | Grand Ballroom BC

 

  1. Names and affiliation of organizers:
  • Nicholas Cummins, Universität Passau, Germany
  • Julien Epps, University of New South Wales, Australia
  • Emily Mower Provost, University of Michigan, USA
  • Thomas Quatieri, MIT Lincoln Laboratory, USA
  • Stefan Scherer, University of Southern California Institute for Creative Technologies, USA

 

  1. Short Description:

A variety of neurological and psychiatric conditions can alter a person’s behavioral signals. Consequently, research that investigates speech as a way to automatically detect and monitor these conditions has become increasingly popular. This is evident from the growing number of publications in this field over the last five years, including the recent Audio/Visual Emotion Challenge Depression Score Prediction Sub-challenges (AVEC 2013 and AVEC 2014), the recent autism and Parkinson’s ComParE challenges at Interspeech 2013 and 2015 respectively, and a depression and suicidality risk assessment tutorial also at Interspeech 2015. However, there is a need to address some key research issues, which are fundamental to characterizing vocal biomarkers for range of neurological and psychiatric conditions.

 

This combination of a special event with a special session is to increase interactions between speech, neuroscience and clinical communities. The aim of this event is to expose speech processing based neurological and psychiatric research to a wider audience and to foster new interdisciplinary collaborations. Potential topics include: the automatic detection and modelling of depression, post-traumatic stress disorder, traumatic brain injury, suicidality, dementia, Alzheimer’s disease, general schizophrenia, Parkinson’s disease and autism.

 

Speech is an attractive signal for use in automated detection of neurological and psychiatric conditions; associated cognitive and physiological alterations influence the process of speech production, affecting the acoustic and linguistic quality of the speech produced in a way that is measurable and possible to objectively assess. However, as speech represents just one potential diagnostic modality, it is important for speech researchers in this field to be conscious of the wide arrange of research into associated biological, physiological and behavioral markers so as to gain an understanding of how speech could be used to augment systems and analysis methods based on these systems. It is also critical that speech researchers gain additional insight into how speech and associated behavioral signals are used in the clinical diagnosis, treatment, and monitoring of these disorders. The special event will provide a focal point for the latest developments within speech-based neurological and psychiatric assessment. On the one hand, the organizers encourage interested speech-based participants to consider submitting full papers to the special session, into one of the following themes, as they are key challenges that span multiple separate application areas in this growing field of speech research:

  • Novel clinically-motivated or neuroscience-motivated analysis methods and vocal features (features designed to capture speech effects specific to one or more conditions)
  • Nuisance Variability Compensation (removing effects of comorbid conditions and other forms of variability that might otherwise limit system performance)
  • Clinical utility and quantifying uncertainty (considerations of clinical utility and systems that can self-determine a level of uncertainty associated with detection, as well as detecting the presence of a condition)
  • Cross-corpus studies (analyzing the potential similarities and differences in speech patterns between the different conditions)

 

On the other hand, the special event will also afford a concentrated opportunity for multidisciplinary interactions; the organizers will advertise the session to potential attendees from psychological, neuroscience and medical backgrounds who may not otherwise attend Interspeech. Participation for these researchers will be through direct invitation of the organizers. The invited participants will be encouraged to present research on one of the following themes:

  • Biological, physiological and behavioral alterations that couple with speech production mechanisms
  • Clinical diagnosis using biological or physiological markers
  • Clinical diagnosis based on observations of behavior variation

 

Speaker Comparison for Forensic and Investigative Applications II

Saturday, 10 September | 10:00 - 12:00 | Grand Ballroom A

 

  1. Names and affiliation of organizers:
  • Jean-François Bonastre, LIA, University of Avignon, France
  • Joseph P. Campbell, MIT Lincoln Laboratory, USA
  • Anders Eriksson, Stockholm University, Sweden
  • Hiro Nakasone, Federal Bureau of Investigation, USA
  • Reva Schwartz, National Institute of Standards and Technology, USA

 

  1. Short Description:

The aim of this special event is to have several structured discussions on speaker comparison for forensic and investigative applications, where many international experts will present their views and participate in the free exchange of ideas. In speaker comparison, speech samples are compared by humans and/or machines for use in investigations or in court to address questions that are of interest to the legal system. Speaker comparison is a high-stakes application that can change people’s lives and it demands the best that science has to offer; however, methods, processes, and practices vary widely. These variations are not necessarily for the better and, although recognized, are not generally appreciated and acted upon. Methods, processes, and practices grounded in science are critical for the proper application (and nonapplication) of speaker comparison to a variety of international investigative and forensic applications. This event follows the successful Interspeech 2015 special event of the same name.

 

  3. Event URL:

http://lia.univ-avignon.fr/es/content/speaker-comparison

 

Speech Ventures

Monday, 12 September | 10:00 - 12:00 | Grand Ballroom A

 

  1. Names and affiliation of organizers:
  • Korbinian Riedhammer, Remeeting, USA
  • Nicolas Scheffer, Facebook, USA
  • Alexandre Lebrun, Facebook, USA
  • David Suendermann-Oeft, ETS, USA

 

  1. Short Description:

Interspeech 2016, the world’s largest conference on speech technologies to be held in San Francisco, the heart of Silicon Valley, provides a unique opportunity to present the most recent developments and ideas of both academia and industry. Located at the cross-section of the two, small and medium-size companies that are interested in using speech in their products or that want to share their experience in doing so, are invited to participate in the speech venture special event. This event provides a platform for participants to interact with the brightest speech researchers and present and discover new trends in spoken language technology. There will be speakers of Analytic Measures, Audeme, Ava, Deepgram, Elsa Now, GoVivace, Jibo, Keen Research, Linguwerk, Oben, Pop Up Archive, Pullstring, Qurious, Remeeting, Verbumware, voice2choice, VoiceBase, api.ai, and emr.ai.

 

COMPUTATIONAL APPROACHES TO LINGUISTIC CODE SWITCHING

Monday, 12 September | 12:15 - 13:00 | Grand Ballroom A

 

  1. Names and affiliation of organizers:
  • Mona Diab, George Washington University, USA
  • Pascale Fung, Hong Kong University of Science and Technology, Hong Kong 
  • Julia Hirschberg, Columbia University, USA 
  • Thamar Solorio, University of Houston, USA 

 

  1. Short Description:

Code-switching (CS) is the phenomenon by which multilingual speakers switch back and forth between their common languages in written or spoken communication. CS may occur at the inter-utterance, intra-utterance (mixing of words from multiple languages in the same utterance) and even morphological (mixing of morphemes from different languages) levels. CS presents serious challenges for language technologies such as Automatic Speech Recognition, Language Modeling, Parsing, Machine Translation (MT), Information Retrieval (IR) and Extraction (IE), Keyword Search, and semantic processing. A prime example of this is acoustic modeling and language modeling in automatic speech recognition (ASR): techniques trained on one language quickly break down when there is mixed language input. The lack of basic tools such as language models, part-of-speech (POS) taggers and parsers trained on such mixed language data makes downstream tasks even more challenging. Even for problems that are largely considered solved for monolingual corpora, such as Language Identification, or POS Tagging, performance degrades at a rate proportional to the amount and level of mixed-language present in the data.

 

This special event is to bring together researchers interested in solving the CS problem, to raise community awareness of the (limited) resources available and the work currently underway for the study of CS, with particular emphasis on work in the speech community. The format will consist of a short introduction from the organizers followed by discussion. We held a workshop in CS in conjunction with EMNLP 2014, developing a shared text-based task for this purpose. We received 18 regular workshop submissions and accepted 8. The goal of this event is to engage the speech processing community now working in this area and to encourage new research by those now working primarily with monolingual corpora.

 

We will solicit participation from researchers working in speech processing for the analysis and/processing of CS data. Topics of relevance to the event will include the following:

  • Methods for improving ASR acoustic and language models in code switched data
  • Domain/dialect/genre adaptation techniques applied to CS data processing
  • Challenges of language identification in CS data.
  • Speech-to-speech translation in CS data
  • Keyword search in CS data
  • Cross-lingual approaches to CS
  • Development of corpora to support research on CS data
  • Crowdsourcing approaches for the annotation of code switched data

 

  1. Event URL: 

https://sites.google.com/site/specialsessiononcodeswitching/home

 

Young Female Researchers in Speech Science & Technology

(BY INVITATION ONLY)

Thursday, 8 September | 09:00 - 16:00 | 1 Market Street, Suite 400, Spear Tower, San Francisco | Room 1MST-4-Charles Crocker

 

  1. Names and affiliation of organizers:
  • Co-Chair: Abeer Alwan, University of California, Los Angeles, USA
  • Co-Chair: Julia Hirschberg, Columbia University, USA
  • Mary Beckman, Ohio State University, USA
  • Carol Espy-Wilson, University of Maryland at College Park, USA
  • Dilek Hakkani-Tur, Microsoft, USA
  • Pascale Fung, Hong Kong University of Science and Technology, Hong Kong
  • Esther Judd, ReadSpeaker, USA
  • Lori Lamel, LIMSI, France
  • Karen Livescu, TTI-Chicago, USA
  • Yang Liu, University of Texas Dallas, USA
  • Helen Meng, The Chinese University of Hong Kong, Hong Kong
  • Mari Ostendorf, University Washington, USA
  • Bhuvana Ramabhadran, IBM, USA
  • Liz Shriberg, SRI International, USA
  • Isabel Trancoso, INESC, Portugal
  • Petra Wagner, University Bielefeld, Germany

 

  1. Short Description:

Women in Science is a workshop for women undergraduate and masters students who are currently working in speech science and technology at Interspeech 2016. This workshop is designed to foster interest in research in our field in women at the undergraduate or masters level who have not yet committed to getting a PhD in speech science or technology areas but who have had some research experience in their college and universities on individual or group projects. The motivation for the workshop is the realization on the part of many women in our field that there seem to be relatively few younger women at Interspeech conferences in the ‘pipeline’ to careers in speech. We wish to address this problem by providing a venue where younger students can present their work with more senior women as mentors and where senior women can describe their own research experience to the students.

 

  1. Event URL:

http://sites.google.com/site/yfrsw2016