Sivan:D

Brooklyn, NY

I am a 2nd-year Ph.D. student in Computer Science advised by Juan Bello at the Music and Audio Research Lab, New York University, in Brooklyn, NY. I am mesmerized by human perception and embodiment, especially auditory perception, and how we model them in machines: machine listening and music information retrieval. My research goal is to make machines that can understand, deconstruct, and create sound. I’m interested in exploring compositionality, disentanglement, and generalizability in audio representation learning.

Previously, I worked as a research intern at Dolby Laboratories with wonderful people in San Francisco on all the cool stuff about spatial audio. I earned my master’s degree in data science from Columbia University in the City of New York, where I often found myself sneaking into the Computer Music Center for some sound art. I hold a bachelor’s degree in energy engineering (thermodynamics) at Wuhan University, China.

I make music and geek out on lots of things in my increasingly squeezed spare time, which you can learn more about on my “fun” website at sivan.fun.

News

May 20, 2024	Research Intern at Dolby, San Francisco.
Oct 23, 2023	2nd time volunteering at SANE Workshop 2023 hosted by MARL.
Sep 05, 2023	I started my Ph.D. journey at MARL, NYU.
Jul 08, 2023	Summer school on funk/fusion at Berklee College of Music, Boston.
Jun 03, 2023	First ICASSP in Rhodes, Greece with paper SAMO.

Latest Posts

Selected Publications

ICASSP

SAMO: Speaker Attractor Multi-Center One-Class Learning For Voice Anti-Spoofing

Siwen Ding, You Zhang, and Zhiyao Duan

In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhode Island, Greece , 2023

Abs DOI Video Code

Voice anti-spoofing systems are crucial auxiliaries for automatic speaker verification (ASV) systems. A major challenge is caused by unseen attacks empowered by advanced speech synthesis technologies. Our previous research on one-class learning has improved the generalization ability to unseen attacks by compacting the bona fide speech in the embedding space. However, such compactness lacks consideration of the diversity of speakers. In this work, we propose speaker attractor multi-center one-class learning (SAMO), which clusters bona fide speech around a number of speaker attractors and pushes away spoofing attacks from all the attractors in a high-dimensional embedding space. For training, we propose an algorithm for the co-optimization of bona fide speech clustering and bona fide/spoof classification. For inference, we propose strategies to enable anti-spoofing for speakers without enrollment. Our proposed system outperforms existing state-of-the-art single systems with a relative improvement of 38% on equal error rate (EER) on the ASVspoof2019 LA evaluation set.
ICASSP

Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms

Iran R. Roman, Christopher Ick, Sivan Ding, and 3 more authors

In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea , 2024

Abs DOI Code

Sound event localization and detection (SELD) is an important task in machine listening. Major advancements rely on simulated data with sound events in specific rooms and strong spatio-temporal labels. SELD data is simulated by convolving spatialy-localized room impulse responses (RIRs) with sound waveforms to place sound events in a soundscape. However, RIRs require manual collection in specific rooms. We present SpatialScaper, a library for SELD data simulation and augmentation. Compared to existing tools, SpatialScaper emulates virtual rooms via parameters such as size and wall absorption. This allows for parameterized placement (including movement) of foreground and background sound sources. SpatialScaper also includes data augmentation pipelines that can be applied to existing SELD data. As a case study, we use SpatialScaper to add rooms to the DCASE SELD data. Training a model with our data led to progressive performance improves as a direct function of acoustic diversity. These results show that SpatialScaper is valuable to train robust SELD models.