#ASRU2023 We build 𝗟𝗧𝗨-𝗔𝗦, the first audio and speech LLM that can simultaneously recognize and jointly understand spoken text, speech paralinguistics, and non-speech audio events - almost 𝗘𝗩𝗘𝗥𝗬𝗧𝗛𝗜𝗡𝗚 perceivable from audio signals. Code at github.com/YuanGongND/ltu.

If you are attending #ASRU2023 , come check out our work on Whova!
You can access the paper here 👉🏻 arxiv.org/pdf/2310.06590…

⁦MT Group at FBK⁩ ⁦IEEE ASRU 2023⁩

The details of OWSM’s budget was featured in Shinji Watanabe’s keynote at IEEE ASRU 2023 .

“It would have been a disaster if the paper was rejected”

Today, we presented the summary papers for the Singing Voice Conversion Challenge 2023 and the VoiceMOS Challenge 2023 at ASRU2023! Fully immersed in the great discussions 🗣️

Spoiler: Pretty certain that there will be future editions for these two challenges. Stay tuned ⚡️⚡️

For all the #ASRU2023 attendees: Join us for IEEE local chapter invited talk! We invite Dr. Andreas Stolcke, Distinguished AI Scientist and VP at Uniphore, and Prof. Torbjørn Svendsen from NTNU at Barry Lam Hall (博理館), R101 (Auditorium), NTU, on Dec. 21st. Details in thread.

إيلاف جميل اسلام، مبتعثة سعودية بجامعة شفيلد بالمملكة المتحدة وباحثة في مجال محاكاة التفاعل البشري عبر الصوت باستخدام التعلم العميق، تحصل على المركز الأول في كلية الهندسة وعلى مستوى جميع الكليات في معرض الملصقات العلمية بالجامعة. بحثها المقبول في ASRU2023 سيُنشر قريبًا.

Elaf…

Will be at #ASRU2023 for next five days to present FastConformer work, come say Hi. Below is my pic with my fav professor Prasanta.

Coming up at #asru2023 (13:30 local time) is my talk on the potential and challenges of using smartphone recordings to monitor health. It will include results from the RADAR-CNS project and an overview of some of my latest work with Jude Dineley and Paula Andrea Perez Toro

If you are in Taipei for #asru2023 , Come check out our Poster.

Come check out the #ASRU2023 poster of the work done during my summer internship at Microsoft Research!

Preprints of FIRNet ( #ICASSP2024 ), ConvNeXt-TTS & ConvNeXt-VC ( #ICASSP2024 ), WaveNeXt ( #ASRU2023 ), Multi-stream HiFi-GAN ( #ASRU2021 ), etc. now available on #NICT ASTL website.
Please check them up!!
ast-astrec.nict.go.jp/en/release/pre…

Our ML-SUPERB paper on multilingual speech self-supervised learning has been accepted by #INTERSPEECH2023 .

Read the paper at arxiv.org/abs/2305.10615 for details on the framework and benchmark design.

We are also launching ML-SUPERB as a challenge at #ASRU2023 . Check it out!

Our paper 'Coco-Nut: Corpus of Japanese Utterance and Voice Characteristics Description for Prompt-based Control' was accepted for #ASRU2023 !

論文がASRU2023にアクセプトされました！

arXiv↓
arxiv.org/abs/2309.13509

Join us for an enlightening afternoon with distinguished speech researchers, Dr. Andreas Stolcke and Prof. Torbjørn Svendsen. Their talks will take place at Barry Lam Hall (博理館) (reurl.cc/krNxl9), R101 (Auditorium), NTU, on December 21st, starting at 2:20PM. #ASRU2023

Reviewing is a very valuable (and often invisible and not much appreciated) service to the community, we are proud about Fede's recognition from #ASRU2023 !

Very interesting talk by Xuedong Huang (ex-Microsoft, now Zoom AI) at IEEE ASRU 2023: in Microsoft, we wanted to train something like Gemini Pro (multimodal multilingual LLM) but MS gave all our GPUs to Open AI 😂

Taking a minute to celebrate the recognition from IEEE ASRU 2023 😀

Nice group photo at IEEE ASRU 2023 after having 小籠包 soup dumplings on the second day 🥢 w/ Chin and Bayesian 40 friends Eric Chang Shinji Watanabe Marco Siniscalchi

riding the sound waves of asr-llm 🤣 🎙️✈️ From EMNLP 2024 🇸🇬 to NeurIPS Conference 🇺🇸 and onto the acoustic arenas of IEEE ASRU 2023 🇹🇼- all in person from 12/5 to 12/20 - as speech/asr enthusiast(s), we are thrilled ... but hard to have it again

I’m presenting my work on severity-preserving voice conversion this morning at ASRU. Please come along if you are interested! :) #asru2023 IEEE ASRU 2023