IEEE SLT2018 (@SLT2018) header
IEEE SLT2018 (@SLT2018) profile picture

IEEE SLT2018

@SLT2018

Official Twitter account of IEEE SLT2018 Workshop on Spoken Language Technology in Athens, Greece 18-21 December 2018. #SLT2018 for updates. Also on LinkedIn.

 Athens, Greece
slt2018.org
Joined December 2017
  • Tweets89
  • Following29
  • Followers89
69Media
Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)Photo by IEEE SLT2018 (@SLT2018)
@Sanabria_RST presenting his Hierarchical Learning with CTC model #coolwork @LTIatCMU @SLT2018
Image from Siddharth Dalmia (@siddalmia05)
1
2
13
IEEE SLT2018 retweeted
ΑΠΕ-ΜΠΕ (@amna_news) profile picture
ΑΠΕ-ΜΠΕ@amna_news20 Dec 2018
#Live #SLT2018 Διεθνές συνέδριο για τις τεχνολογίες ομιλίας στην Ελλάδα (@SLT2018) Η ομιλία της Δήμητρας Βεργύρη, διευθύντριας του Speech Technology and Research Laboratory του @SRI_Intl youtube.com/watch?v=TPf89aPs…
Διεθνές συνέδριο για τις τεχνολογίες ομιλίας στην Ελλάδα

Διεθνές συνέδριο για τις τεχνολογίες ομιλίας στην Ελλάδα

Ζωντανή μετάδοση της ομιλίας της κας. Δήμητρας Βεργύρη, διευθύντρια...

youtube.com
3
3
IEEE SLT2018 retweeted
IEEE SLT2018 (@SLT2018) profile picture
IEEE SLT2018@SLT201818 Dec 2018
#SLT2018 poster session time in Kallirhoe Hall Deep Learning for Speech Synthesis session.
Image from IEEE SLT2018 (@SLT2018)
Image from IEEE SLT2018 (@SLT2018)
Image from IEEE SLT2018 (@SLT2018)
Image from IEEE SLT2018 (@SLT2018)
2
1
4
Poster sessions have some serious #innovation in #speechrecognition & #voiceAI to showcase, at @SLT2018
Image from Behavioral Signals (@behaviorsignals)
Image from Behavioral Signals (@behaviorsignals)
1
1
4
It's been a real honour today addressing the #SLT2018 plenary during the official opening with my fellow chairs Y. Stylianou @Apple and S.Bangalore, Interactions
Image from Vangelis Karkaletsis (@VangKarkaletsis)
Image from Vangelis Karkaletsis (@VangKarkaletsis)
Image from Vangelis Karkaletsis (@VangKarkaletsis)
Image from Vangelis Karkaletsis (@VangKarkaletsis)
2
1
9
Finding the 'chunks' in #Alexa utterances. A robust method to parse the coordinations in sentences like "add peanut butter and jelly to my list” and “play songs by Queen and Davie Bowie”. Blog post, @SLT2018 paper from @irodov_rg @arindaman et al #AlexaAI amzn.to/2S7UtHH
Image from Stephen Potter (@PotterAtWork)
1
1
4
Clever data representations — such as "embeddings" — are vital to the success of natural-language AI systems. At @SLT2018, Alexa researchers present a new data representation that cuts Alexa's skill selection error rate by 40%. #AlexaAI developer.amazon.com/blogs/a…
4
1
9
IEEE SLT2018 retweeted
IEEE SLT2018 (@SLT2018) profile picture
IEEE SLT2018@SLT201816 Dec 2018
The #SLT2018 task force at work! Our team is working full speed ahead preparing material for the @SLT2018 conference starting onTuesday 18 December 2018! Take a sneak peek at our Christmassy conference goodie bags! 🎄
Image from IEEE SLT2018 (@SLT2018)
Image from IEEE SLT2018 (@SLT2018)
Image from IEEE SLT2018 (@SLT2018)
2
5
.@IEEEorg Spoken Language Technology Workshop is starting tomorrow in Athens, Greece! Our team with Quentin Furhatino will be there showcasing how we capture emotional cues in speech! Stay tuned! #emotionrecognition #SLT2018
Image from Behavioral Signals (@behaviorsignals)
1
4
Check our new AudioVisual approach with CTC/Attention loss. We attain 63.5% WER on the challenging LRS2 using visual-only information, and 7.0% WER with early AudioVisual fusion, compared to 8.3% WER with audio-only (accepted at @SLT2018 ). arxiv.org/abs/1810.00108
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture

Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture

Recent works in speech recognition rely either on connectionist temporal classification (CTC) or sequence-to-sequence models for character-level recognition. CTC assumes conditional independence...

arxiv.org
1
1
4
Load more