
Speech technology researcher/manager @AssemblyAI
Bellevue, WA
Joined November 2016
- Tweets910
- Following56
- Followers542
- Likes2.5K
Takuya Yoshioka retweeted
Want to hear a friend in a noisy café? We designed deep learning-based headphones that let you isolate the speech from a specific person just by *looking* at them for a few seconds. CHI'24 honorable mention award.
Paper: arxiv.org/abs/2405.06289
Code: github.com/vb000/LookOnceToH…
Takuya Yoshioka retweeted
I got an early demo of this when I visited @uwcse a couple months ago and the ability to isolate sounds in your environment was pretty great. Nice work, @b_veluri, Malek Itani, Tuochao Chen, Takuya Yoshioka, and @ShyamGollakota!
Want to hear a friend in a noisy café? We designed deep learning-based headphones that let you isolate the speech from a specific person just by *looking* at them for a few seconds. CHI'24 honorable mention award.
Paper: arxiv.org/abs/2405.06289
Code: github.com/vb000/LookOnceToH…
Takuya Yoshioka retweeted
Hi all, please let me know if you know large-scale speech data that can be used for training our Whisper reproduction (OWSM) model (arxiv.org/abs/2309.13876). We plan to move to OWSM v4.
Creating speech zones with self-distributing acoustic swarms
Our latest paper in Nature Communications unveils distributed microphones based on an autonomous acoustic robotic swarm, creating "speech zones" in real-world settings.
Paper: nature.com/articles/s41467-0…
The code and project page are here.
Code: github.com/uw-x/AcousticSwar…
Project page: acousticswarm.cs.washington.…
1
440
Last Friday marked the end of my 7-year journey at Microsoft, filled with rewarding challenges, both in research & production, and incredible colleagues. I'll be starting something new very soon.
マイクロソフトを退職しました。まだずっとシアトル界隈にいます。
Takuya Yoshioka retweeted
SpeechX: Neural Codec Language Model as a Versatile Speech Transformer
paper page: huggingface.co/papers/2308.0…
Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks, dealing with both clean and noisy signals. SpeechX combines neural codec language modeling with multi-task learning using task-dependent prompting, enabling unified and extensible modeling and providing a consistent way for leveraging textual input in speech enhancement and transformation tasks. Experimental results show SpeechX's efficacy in various tasks, including zero-shot TTS, noise suppression, target speaker extraction, speech removal, and speech editing with or without background noise, achieving comparable or superior performance to specialized models across tasks.
SpeechX from our new paper is a single generative model that edits, enhances & creates speech, enabling zero-shot TTS, spoken content editing (while preserving ambience), speaker extraction & speech/noise removal.
Demo: aka.ms/speechx
Paper: arxiv.org/abs/2308.06873
Takuya Yoshioka retweeted
To everyone booking their @IEEE_WASPAA trip: please consider attending #SANE2023, which will take place at NYU on Thursday October 26, the day after #WASPAA2023.
Register at saneworkshop.org/sane2023/
Dear #WASPAA2023 authors, the review results are out now. Please go ahead and check out at cmt3.research.microsoft.com/…. We appreciate your precious contribution and kind interest regardless of the acceptance decision!
Takuya Yoshioka retweeted
Replying to @ieeeICASSP
@ieeeICASSP Are there poster printing facilities at/near the conference venue?
Real-time target sound extraction with waveformer (to appear in ICASSP). Joint work with UW researchers.
Paper (updated): arxiv.org/abs/2211.02250
Demo: waveformer.cs.washington.edu…
Code (both causal and non-causal): github.com/vb000/Waveformer
Takuya Yoshioka retweeted
WASPAA 2023 calls for papers! The traditional intimate Mohonk Mountain House with exciting changes: double-blind review, an unprecedented amount of travel grants, and more. More information: waspaa.com/call-for-papers/ #waspaa2023
Takuya Yoshioka retweeted
すごい!
世界最大1万9千時間の音声コーパスと高精度日本語音声認識モデルがオープンソースで公開 - 窓の杜 forest.watch.impress.co.jp/d… via @madonomori
Takuya Yoshioka retweeted
The #ICASSP2023 paper submission site is now open! Submit your papers by 19 October 2022 to be considered. Learn more about the paper guidelines and submission requirements here: hubs.la/Q01nmxt_0
How can we do streaming multi-talker ASR by best combining speech separation and overlap-robust ASR?
t-SOT-VA does that and works for real meeting audio with any # of mics, achieving the best published WERs of 13.7%/15.5% for AMI-MDM dev/eval.
Paper: arxiv.org/abs/2209.04974
Takuya Yoshioka retweeted
Please retweet,
@Lam19Tk, a young MT researcher, soon-to-be-PhD needs your help. He is looking for a job in speech/text translation. A job he already had lined-up has been revoked due to the hiring freezes in the industry.
Here's his linkedin profile:
linkedin.com/in/tsz-kin-lam-…
Our new work on speaker diarization: arxiv.org/abs/2208.13085
(1) TS-VAD with cross-speaker transformer achieves a new SOTA DER in VoxConverse. (2) Further EEND-EDA integration for one-step diarization brings down the DER in CALLHOME.
Takuya Yoshioka retweeted
The challenge submission deadline is approaching (Sep 26). If you're interested in it, please do not hesitate to ask the CHiME Steering Group ([email protected]) or members (chimechallenge.org/current/s…) individually!
Call for proposals!
We now wish to introduce a more open model, where the annual CHiME Challenge features independent tasks organized by teams who work within a schedule defined by the CHiME Steering Group. See chimechallenge.org/current/c…
Takuya Yoshioka retweeted
TTIC celebrates the life of Sadaoki Furui ttic.edu/news/#0822-3
Takuya Yoshioka retweeted
Hi all, SLT'22 will organize a hackathon event. Please check slt2022.org/hackathon.php The application deadline is Sep. 30th! @ieee_slt



















