Thrilled to share that I presented a paper at the prestigious #ICASSP2024 in Seoul π°π·! Alongside academic pursuits, I had the opportunity to immerse myself in the vibrant city of Seoul. From the rich culinary delights to the dynamic culture, every moment was captivating. Theβ¦
with Xavier Riley: High-resolution guitar transcription via domain adaptation! Accepted at IEEE ICASSP #ICASSP2024 π°π·πΈπ more details to follow... βοΈ
π¨ π’ There is still a chance to have your paper appear in ICASSP through our XAI-SA workshop. If you have ongoing work on Explainable AI for Speech/Audio, consider sending a paper to our workshop!
xai-sa-workshop.github.io
#ICASSP2024
π Exciting news! π’ Six works accepted between the main conference and workshops at #ICASSP2024 ! π
Let me walk you through each one!
Looking forward to discussing them with you in Seoul in a few days! π°π·ποΈ
I had a very productive 6 days, interacting and discussing with many great researchers!
Thank you very much to everyone involved!
#ICASSP2024
Awesome experience in my hometown with splendid conference #ICASSP2024 π Fully motivated to submit paper for next #ICASSP2025 βοΈ
π₯³ We present our #ICASSP2024 paper:
A diffusion model that generates production-quality (bass) audio stems to any audio input. ππΈ According to our experience, that's more useful to artists than generating full mixes. π
πPaper: arxiv.org/abs/2402.01412
πΆDemo:β¦
I'm excited to share that our paper has been accepted at #ICASSP2024 :
Improving ASR Contextual Biasing with Guided Attention
Jiyang Tang, Kwangyoun Kim, Suwon Shon, Felix Wu Felix Wu, Prashant Sridhar, Shinji Watanabe Shinji Watanabe
(Will add an Arxiv link soon :)
(1/3)
It was a real pleasure to share my two works on childrenβs ASR using Adapter and TTS data augmentation at #ICASSP2024 in Seoul π°π·
I presented our work in #ICASSP2024 in Korea. I really enjoyed my first onsite conference. It was pleasure to meet wonderful researchers!
This is the link to our paper. Feel free to send me messages!
ieeexplore.ieee.org/document/10445β¦
New paper in #ICASSP2024 π
Self-supervised adaptive pre-training (SAPT) on task data (aka don't stop pre-training) is effective for NLP π€ & visionποΈ
But... is this also true for speech models? π€
In our paper, we investigate this question π
π arxiv.org/pdf/2312.07338β¦
1\π§΅
Our lab member Mr. Kentaro Seki is presenting his work related to the core-set selection for TTS π§Ό #ICASSP2024
I presented my first ever paper in a top conference at #ICASSP2024 in Seoul π°π·. Feeling grateful for this amazing opportunity. The path to this moment hasnβt been easy, but the journey is worth it. Tons of insightful discussions and new connections made at the conferenceβ¦
π½οΈCheck out video highlights from the second half of #ICASSP2024 below! View the full video on YouTube here: hubs.la/Q02tNgMZ0