Adobe at Top Audio Conferences in 2021

January 31, 2022

Adobe co-authored 21 papers at top audio conferences in 2021 – twelve papers at ICASSP, six at WASPAA and three at ISMIR – with topics ranging from high quality speech synthesis to cross-modal music retrieval, automatic optimization of DSP algorithms, few-shot audio recognition, HRTF modelling, and many more.  

Three Adobe Research co-authored papers received awards at WASPAA 2021 and ISMIR 2021. Adobe researchers also served as chairs or committee members for all three conferences.  

Nearly all of Adobe co-authored papers are the result of student internships or other collaborations with university students and faculty. Check out the Adobe Research Careers website to learn more about internships and full-time career opportunities

ICASSP 2021 (June 5 – 11, 2021) 

Bandwidth Extension Is All You Need 
Jiaqi Su, Yunyun Wang, Adam Finkelstein, Zeyu Jin  
 
CDPAM: Contrastive Learning for Perceptual Audio Similarity 
Pranay Manocha, Zeyu Jin, Richard Zhang, Adam Finkelstein 
 
Communication-Cost Aware Microphone Selection for Neural Speech Enhancement with Ad-Hoc Microphone Arrays 
Jonah Casebeer, Jamshed Kaikaus, Paris Smaragdis  
 
Context-Aware Prosody Correction For Text-Based Speech Editing 
Max Morrison, Lucas Rencker, Zeyu Jin, Nicholas Bryan, Juan-Pablo Caceres, Bryan Pardo 
 
Differentiable Signal Processing With Black-Box Audio Effects 
Marco Martınez Ramırez, Oliver Wang,  Paris Smaragdis, Nicholas Bryan  
 
Few-Shot Continual Learning For Audio Classification 
Yu Wang, Nicholas Bryan, Mark Cartwright, Juan Pablo Bello, Justin Salamon 
 
LIFI: Towards Linguistically Informed Frame Interpolation 
Aradhya Neeraj Mathur, Devansh Batra, Yaman Kumar, Rajiv Ratn Shah, Roger Zimmermann, Changyou Chen 
 
Optimizing Short-Time Fourier Transform Parameters Via Gradient Descent 
An Zhao, Krishna Subramani, Paris Smaragdis 
 
Personalized HRTF Modeling Using DNN-augmented BEM 
Mengfan Zhang, Jui-Hsien Wang, Doug James 
 
Sound Event Detection And Separation: A Benchmark On DESED Synthetic Soundscapes 
Nicolas Turpault, Romain Serizel, Scott Wisdom, Hakan Erdogan, John Hershey, Eduardo Fonseca, Prem Seetharaman, Justin Salamon 
 
Unified Gradient Reweighting for Model Biasing with Applications to Source Separation 
Efthymios Tzinis, Dimitrios Bralios, Paris Smaragdis 
 
What’s All The Fuss About Free Universal Sound Separation Data? 
Scott Wisdom, Hakan Erdogan, Daniel Ellis, Romain Serizel, Nicolas Turpault, Eduardo Fonseca, Justin Salamon, Prem Seetharaman, John Hershey 

WASPAA 2021 (October 17 – 20, 2021) 

Auto-DSP: Learning to Optimize Acoustic Echo Cancellers 
Jonah Casebeer, Nicholas Bryan, Paris Smaragdis 
 
HiFi-GAN-2: Studio-quality speech enhancement via generative adversarial networks conditioned on acoustic features 
Jiaqi Su, Zeyu Jin, Adam Finkelstein 
 
Point Cloud Audio Processing 
Krishna Subramani, Paris Smaragdis 
Best Paper Award 
 
Separate but Together: Unsupervised Federated Learning for Speech Enhancement From Non-IID Data 
Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, Paris Smaragdis 
 
Sound Event Detection With Adaptive Frequency Selection 
Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, Paris Smaragdis 
 
Who Calls the Shots? Rethinking Few-Shot Learning for Audio 
Yu Wang, Nicholas Bryan, Justin Salamon, Mark Cartwright, Juan Pablo Bello 
Best Audio Few-Shot Learning Paper Award 

ISMIR 2021 conference (November 8 – 12, 2021) 

Controllable deep melody generation via hierarchical music representation 
Shuqi Dai, Zeyu Jin, Celso Gomes, Roger Dannenberg 
 
Deep Embeddings and Section Fusion Improve Music Segmentation 
Justin Salamon, Oriol Nieto, Nicholas Bryan 
 
Emotion Embedding Spaces for Matching Music to Stories 
Minz Won, Justin Salamon, Nicholas Bryan, Gautham Mysore, Xavier Serra 
Best Student Paper Award 

Related Posts