Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡· (@beomseok_lee_) 's Twitter Profile
Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡·

@beomseok_lee_

PhD student @uniTrento. Affiliated in @naverlabseurope and @fbk_mt. Ex research engineer @samsungresearch

ID: 1685560120292290560

linkhttps://www.linkedin.com/in/beomseok-lee-b29b798a/ calendar_today30-07-2023 07:57:19

9 Tweet

29 Followers

135 Following

Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡· (@beomseok_lee_) 's Twitter Profile Photo

πŸ™‹πŸ»β€β™‚οΈIs the saying "Two heads are better than one." the case for multi-modal learning? well, only if two act as one. Find out how two heads(modalities) are better than one(modality). On Uni-Modal Feature Learning in Supervised Multi-Modal Learning arxiv.org/abs/2305.01233 MT Group at FBK

Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡· (@beomseok_lee_) 's Twitter Profile Photo

An interesting paper related to the Spoken Language Understanding (SLU) topic. Can we build a single model that performs multiple SLU tasks? -> YES! Check out the details from the paper. arxiv.org/abs/2310.02973 MT Group at FBK

Marcely Z. Boito @ Interspeech 2024 πŸ‡¬πŸ‡· (@mzboito) 's Twitter Profile Photo

πŸš€ Exciting News! mHuBERT-147 is Here! πŸš€ We've just released mHuBERT-147, a compact powerful multilingual model, reaching top position on ML-SUPERB with just 95M parameters! 🌟 Trained on balanced, high-quality, open-license data, this model rivals MMS-1B but is 10x smaller.

πŸš€ Exciting News! mHuBERT-147 is Here! πŸš€

We've just released mHuBERT-147, a compact powerful multilingual model, reaching top position on ML-SUPERB with just 95M parameters! 🌟

Trained on balanced, high-quality, open-license data, this model rivals MMS-1B but is 10x smaller.
Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡· (@beomseok_lee_) 's Twitter Profile Photo

Check out how discrete speech units can be fed to the Large Language Model for Spoken Question Answering (SQA) task in this paper. Also, do not miss several interesting findings presented in the experiments! arxiv.org/abs/2406.09345 MT Group at FBK

MT Group at FBK (@fbk_mt) 's Twitter Profile Photo

Meet the FBK MT group at #INTERSPEECH2024 next week! πŸ‡¬πŸ‡· Our Beomseok LEE will attend the conference and present the following paper! More info is available on our website: mt.fbk.eu/1-paper-accept… #INTERSPEECH2024 #SPEECH #SLU

Marcely Z. Boito @ Interspeech 2024 πŸ‡¬πŸ‡· (@mzboito) 's Twitter Profile Photo

🚨 Demo Alert! 🚨 πŸ”₯ mHuBERT-147 + speech-MASSIVE = French SLU! πŸ”₯ Next week, Beomseok LEE and I will be in Kos πŸ‡¬πŸ‡· presenting two brand-new speech resources from NAVER LABS Europe πŸ€– To showcase them, we've prepared this Hugging Face demo: huggingface.co/spaces/naver/F…

MT Group at FBK (@fbk_mt) 's Twitter Profile Photo

Our Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡· presenting "Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond" at #INTERSPEECH2024 πŸ‡¬πŸ‡· Check here for more details: arxiv.org/abs/2408.03900

Our <a href="/beomseok_lee_/">Beomseok LEE @ INTERSPEECH πŸ‡¬πŸ‡·</a> presenting "Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond" at #INTERSPEECH2024 πŸ‡¬πŸ‡·

Check here for more details:
arxiv.org/abs/2408.03900