BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Semi-supervised Learning for Low-resource Multilingual and Multimo
 dal Speech Processing with Machine Speech Chain - Prof Sakriani Sakti\, Na
 ra Institute of Science and Technology (NAIST)\, Japan
DTSTART:20210223T120000Z
DTEND:20210223T130000Z
UID:TALK156772@talks.cam.ac.uk
CONTACT:Dr Kate Knill
DESCRIPTION:*Abstract:*\nThe development of advanced spoken language techn
 ologies based on automatic speech recognition (ASR) and text-to-speech syn
 thesis (TTS) has enabled computers to either learn how to listen or speak.
  Many applications and services are now available but still support fewer 
 than 100 languages. Nearly 7000 living languages that are spoken by 350 mi
 llion people remain uncovered. This is because the construction is commonl
 y done based on machine learning trained in a supervised fashion where a l
 arge amount of paired speech and corresponding transcription is required.\
 n\nIn this talk\, we will introduce a semi-supervised learning mechanism b
 ased on a machine speech chain framework. First\, we describe the primary 
 machine speech chain architecture that learns not only to listen or speak 
 but also to listen while speaking. The framework enables ASR and TTS to te
 ach each other given unpaired data. After that\, we describe the use of ma
 chine speech chain for code-switching and cross-lingual ASR and TTS of sev
 eral languages\, including low-resourced ethnic languages. Finally\, we de
 scribe the recent multimodal machine chain that mimics overall human commu
 nication to listen while speaking and visualizing. With the support of ima
 ge captioning and production models\, the framework enables ASR and TTS to
  improve their performance using an image-only dataset.\n\n*Biography:*\nS
 akriani Sakti is currently a research associate professor at Nara Institut
 e of Science and Technology (NAIST) and a research scientist at RIKEN Cent
 er for Advanced Intelligent Project (RIKEN AIP)\, Japan. She received DAAD
 -Siemens Program Asia 21st Century Award in 2000 to study in Communication
  Technology\, University of Ulm\, Germany\, and received her MSc degree in
  2002. During her thesis work\, she worked with the Speech Understanding D
 epartment\, DaimlerChrysler Research Center\, Ulm\, Germany. She then work
 ed as a researcher at ATR Spoken Language Communication (SLC) Laboratories
  Japan in 2003-2009\, and NICT SLC Groups Japan in 2006-2011\, which estab
 lished multilingual speech recognition for speech-to-speech translation. W
 hile working with ATR and NICT\, Japan\, she continued her study (2005-200
 8) with Dialog Systems Group University of Ulm\, Germany\, and received he
 r Ph.D. degree in 2008. She was actively involved in international collabo
 ration activities such as Asian Pacific Telecommunity Project (2003-2007) 
 and various speech-to-speech translation research projects\, including A-S
 TAR and U-STAR (2006-2011). In 2011-2017\, she was an assistant professor 
 at the Augmented Human Communication Laboratory\, NAIST\, Japan. She also 
 served as a visiting scientific researcher of INRIA Paris-Rocquencourt\, F
 rance\, in 2015-2016\, under JSPS Strategic Young Researcher Overseas Visi
 ts Program for Accelerating Brain Circulation. Since January 2018\, she se
 rves as a research associate professor at NAIST and a research scientist a
 t RIKEN AIP\, Japan. She is a member of JNS\, SFN\, ASJ\, ISCA\, IEICE\, a
 nd IEEE. Furthermore\, she is currently a committee member of IEEE SLTC (2
 021-2023) and an associate editor of the IEEE/ACM Transactions on Audio\, 
 Speech\, and Language Processing (2020-2023). She was a board member of Sp
 oken Language Technologies for Under-resourced languages (SLTU) and the ge
 neral chair of SLTU2016. She was also the general chair of the "Digital Re
 volution for Under-resourced Languages (DigRevURL)" Workshop as the Inters
 peech Special Session in 2017 and DigRevURL Asia in 2019. She was also the
  organizing committee of the Zero Resource Speech Challenge 2019 and 2020.
  She was also involved in creating joint ELRA and ISCA Special Interest Gr
 oup on Under-resourced Languages (SIGUL) and served as SIGUL Board since 2
 018. Last year\, in collaboration with UNESCO and ELRA\, she was also the 
 organizing committee of the International Conference of "Language Technolo
 gies for All (LT4All): Enabling Linguistic Diversity and Multilingualism W
 orldwide". Her research interests lie in deep learning & graphical model f
 ramework\, statistical pattern recognition\, zero-resourced speech technol
 ogy\, multilingual speech recognition and synthesis\, spoken language tran
 slation\, social-affective dialog system\, and cognitive-communication.\n\
 nThis talk is made possible through the ISCA International Virtual Seminar
 s.
LOCATION:Zoom: https://zoom.us/j/95352633552?pwd=RzJVK2UzOGZyNU5mVHd1Y1VPT
 2tDUT09
END:VEVENT
END:VCALENDAR