Adobe Presents Audio Research in Major Conferences and Journals

February 1, 2023

Tags: AI & Machine Learning, Audio, Conferences

This ICASSP 2022 paper presents a new deep learning approach to enhance low-quality music recordings.

Audio researchers at Adobe co-authored 19 papers at top-tier conferences and journals in 2022. In addition to audio research published at venues such as ICASSP, INTERSPEECH and IWAENC, Adobe researchers work at the intersection of audio and areas such as computer vision and human-computer interaction, leading to publications in CVPR, UIST, and high-impact journals. These publications covered a range of topics in audio AI with applications to speech, music, and everyday sounds including enhancement, editing, audio production, accessibility, and recommendation.

Adobe researchers also served as chairs and committee members at audio conferences including ICASSP and ISMIR, and served on organization boards and committees such as the IEEE Audio and Acoustic Signal Processing Technical Committee and the ISMIR Society board.  

Most of the Adobe co-authored papers are the outcome of research internships. Please check out the Adobe Research careers page to learn more about internships and full-time career opportunities.

ICASSP 2022 

Music Enhancement Via Image Translation and Vocoding 
Nikhil Kandpal, Oriol Nieto, Zeyu Jin 

Controllable Speech Representation Learning Via Voice Conversion and AIC Loss 
Yunyun Wang, Jiaqi Su, Adam Finkelstein, Zeyu Jin 

SQAPP: No-Reference Speech Quality Assessment via Pairwise Preference 
Pranay Manocha, Zeyu Jin, Adam Finkelstein 

Don’t Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization 
Haici Yang, Shivani Firodiya, Nick Bryan, Minje Kim 

End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline 
Tuan Manh Lai, Trung Bui, Doo Soon Kim


DocLayoutTTS: Dataset and Baselines for Layout-informed Document-level Neural Speech Synthesis 
Puneet Mathur, Franck Dernoncourt, Quan Hung Tran, Jiuxiang Gu, Ani Nenkova, Vlad Morariu, Rajiv Jain, Dinesh Manocha 

Audio Similarity is Unreliable as a Proxy for Audio Quality 
Pranay Manocha, Zeyu Jin, Adam Finkelstein 

Filler Word Detection and Classification: A Dataset and Benchmark 
Ge Zhu, Juan-Pablo Caceres, Justin Salamon 

Span Classification with Structured Information for Disfluency Detection in Spoken Utterances 
Sreyan Ghosh, Sonal Kumar, Yaman Kumar, Rajiv Ratn Shah, Srinivasan Umesh 


Meta-Learning for Adaptive Filters with Higher-Order Frequency Dependencie
Junkai Wu, Jonah Casebeer, Nicholas Bryan, Paris Smaragdis 
Published at IWAENC 2022 conference, June 2022   

It’s Time for Artistic Correspondence in Music and Video 
Dídac Surís, Carl Vondrick, Bryan Russell, Justin Salamon 
Published at CVPR 2022 conference, June 2022 

Audio-driven Neural Gesture Reenactment with Video Motion Graphs 
Yang Zhou, Jimei Yang, Dingzeyu Li, Jun Saito, Deepali Aneja, Evangelos Kalogerakis 
Published at CVPR 2022 conference, June 2022 

Record Once, Post Everywhere: Automatic Shortening of Audio Stories for Social Media 
Bryan Wang, Zeyu Jin, Gautham Mysore 
Published at UIST 2022 conference, October 2022 

CrossA11y: Identifying Video Accessibility Issues via Cross-modal Grounding 
Xingyu “Bruce” Liu, Ruolin Wang, Dingzeyu Li, Xiang “Anthony” Chen, Amy Pavel 
Published at UIST 2022 conference, October 2022 
Best Paper Award 

Beyond Subtitles: Captioning and Visualizing Non-speech Sounds to Improve Accessibility of User-Generated Videos 
Oliver Alonzo, Hijung Valentina Shin, Dingzeyu Li 
Published at ASSETS 2022 conference, October 2022  

HEAR: Holistic Evaluation of Audio Representations 
Joseph Turian, Jordie Shier, Humair Raj Khan, Bhiksha Raj, Björn W. Schuller, Christian J. Steinmetz, Colin Malloy, George Tzanetakis, Gissel Velarde, Kirk McNally, Max Henry, Nicolas Pinto, Camille Noufi, Christian Clough, Dorien Herremans, Eduardo Fonseca, Jesse Engel, Justin Salamon, Philippe Esling, Pranay Manocha, Shinji Watanabe, Zeyu Jin, Yonatan Bisk 
Published in Proceedings of Machine Learning Research (PMLR), December 2022. 

Automated Acoustic Monitoring Captures Timing and Intensity of Bird Migration 
Benjamin M. Van Doren, Vincent Lostanlen, Aurora Cramer, Justin Salamon, Adriaan Dokter, Steve Kelling, Juan Pablo Bello, Andrew Farnsworth 
Published in Journal of Applied Ecology, December 2022 

Style Transfer of Audio Effects with Differentiable Signal Processing. 
Christian J. Steinmetz, Nicholas Bryan, Joshua D. Reiss  
Published in Journal of the Audio Engineering Society (JAES), September 2022 

Meta-AF: Meta-learning for Adaptive Filters 
Jonah Casebeer, Nicholas Bryan, Paris Smaragdis 
Published in IEEE Transactions on Audio, Speech, and Language Processing (TASLP), November 2022

Related Posts