@heiga_zen Profile picture

Heiga Zen (全 炳河)

@heiga_zen

Principal Scientist (Director) @GoogleDeepMind . 波瀬小⇒一志中⇒鈴鹿高専⇒名工大 (IBM TJ Watson intern for a year)⇒東芝欧州研⇒Google (Speech🇬🇧⇒Brain🇯🇵) ⇒Google DeepMind

Similar User
arXiv Sound photo

@ArxivSound

Daisuke Okanohara / 岡野原 大輔 photo

@hillbig

Shinji Watanabe photo

@shinjiw_at_cmu

Wei-Ning Hsu photo

@mhnt1580

Hitomi Yanaka (谷中 瞳) photo

@verypluming

Takuya Akiba photo

@iwiwi

Felix Hill photo

@FelixHill84

rohan anil photo

@_arohan_

Odashi photo

@odashi_t

Kenta Oono photo

@delta2323_

Yoshitaka Ushiku photo

@losnuevetoros

Keiichi Tokuda/徳田恵一 photo

@KeiichiTokuda

Yuma Koizumi photo

@yuma_koizumi

Hiroshi Saruwatari photo

@hsaruwatari727

yu4u photo

@yu4u

I was a Google mentor for Prof. Futami featured in this blog post. Really happy to see the fellowship contributed to his research career development!

Congrats to this year's Google PhD Fellows. These are some of the most talented computer science PhD students from around the world, and we look forward to supporting their studies and research! blog.google/technology/res…



Heiga Zen (全 炳河) Reposted

the new dedicated Google Gemini app has hit the US App Store finally apps.apple.com/us/app/google-…


Heiga Zen (全 炳河) Reposted

The #AlphaFold 3 model code and weights are now available for academic use. We @GoogleDeepMind are excited to see how the research community continues to use AlphaFold to address open questions in biology and new lines of research. github.com/google-deepmin…

We love the excitement & results from the community on AlphaFold 3 and are doubling the AF Server daily job limit to 20. Happy to also share that we're working on releasing the AF3 model (incl weights) for academic use, which doesn’t depend on our research infra, within 6 months.



Heiga Zen (全 炳河) Reposted

(日本語) リアルタイムTTSの良い実装ご存じの方いたら教えて欲しいっす.


機内でICASSPの査読してます


ヒースロー空港着


ロンドンはまだ早朝ですが、今から東京・バンガロールとミーティングです。眠い。


Heiga Zen (全 炳河) Reposted

🚀 Join the Gemini Multilinguality team @GoogleDeepMind 🌐 We’re looking for researchers passionate about making LLMs helpful for all. Dramatically improve model quality, coverage, and cultural relevance across hundreds of languages. #NLProc #MultilingualAI #i18n #LLMs


I will be in London next week. Looking forward to reconnecting to friends and meeting new people!


Heiga Zen (全 炳河) Reposted

We also provide reference implementations for the encoder and decoder on GitHub. (Yes, I know no one uses TensorFlow anymore ;P) github.com/google/sequenc…


Heiga Zen (全 炳河) Reposted

Transformer-based TTS models sound great but have all kinds of reliability issues. Our new model, Very Attentive Tacotron (VAT), is a Transformer-based TTS system that doesn't drop or repeat words and can generalize to any practical utterance length. arxiv.org/abs/2410.22179


Heiga Zen (全 炳河) Reposted

Introducing our latest research paper on EMMA, an End-to-End Multimodal Model for autonomous driving! 🤖This cutting-edge AI research highlights the potential to leverage multimodal world knowledge for autonomous driving. Learn more: waymo.com/blog/2024/10/i…

Tweet Image 1

Heiga Zen (全 炳河) Reposted

Our latest generative technology is now powering MusicFX DJ in @LabsDotGoogle - and we’ve also updated Music AI Sandbox, a suite of experimental music tools which can streamline creation. 🎵 This will make it easier than ever to make music in real-time with AI.…

Tweet Image 1

Heiga Zen (全 炳河) Reposted

The applications for advanced speech generation are vast. 🗣️ From improving accessibility and creating new educational experiences to combining these developments with our Gemini models, we’re excited to continue pushing the boundaries of what’s possible. ↓…


Google DeepMind 最高執行責任者 (COO) である ライラ・イブラヒムのインタビューが、日本経済新聞に掲載されました。 ノーベル賞受賞のGoogle子会社、汎用AI「究極の目標」 - 日本経済新聞 nikkei.com/article/DGXZQO…


Heiga Zen (全 炳河) Reposted

``Very Attentive Tacotron: Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech,'' Eric Battenberg, RJ Skerry-Ryan, Daisy Stanton, Soroosh Mariooryad, Matt Shannon, Julian Salazar, David Kao, ift.tt/JQ152zE


Heiga Zen (全 炳河) Reposted

I am hiring for a research engineering role in NYC, focused on Gemini post training. If you are interested, please apply here. Deadline is just in two weeks. boards.greenhouse.io/deepmind/jobs/…


Heiga Zen (全 炳河) Reposted

Since launching AI Overviews earlier this year, people have been asking a whole new universe of questions. With today’s expansion to 100+ countries, AI Overviews will reach 1B+ users globally. More exciting things for Search ahead! blog.google/products/searc…


Loading...

Something went wrong.


Something went wrong.