iZotope Research

Our mission as the iZotope research team is to enable the durable technological competitiveness and scientific leadership of iZotope and its products based on the invention of novel signal processing technology. Read our latest research below. 

Research Highlights

Carve out unwanted noise

Speech Dereverberation using Recurrent Neural Networks

In this paper, we show how a simple reformulation allows us to adapt blind source separation techniques to the problem of speech dereverberation and, accordingly, train a bidirectional recurrent neural network (BRNN) for this task. 

Shahan Nercessian and Alexey Lukin

Work in Daw or App

Zero-shot Singing Voice Conversion


In this paper, we propose the use of speaker embedding networks to perform zero-shot singing voice conversion, and suggest two architectures for its realization.

Shahan Nercessian

RX 8 music rebalance

Moog Ladder Filter Generalizations Based on State Variable Filters

In this paper, we propose a new style of continuous-time filter design composed of a cascade of 2nd-order state variable filters (SVFs) and a global feedback path.

Kurt James Werner and Russell McClellan

Carve out unwanted noise

Neural Parametric Equalizer Matching Using Differentiable Biquads

This paper proposes a neural network for carrying out parametric equalizer (EQ) matching.


Shahan Nercessian 

Research Bibliography

  • Shahan Nercessian, Andy Sarroff, & Kurt James Werner, “Lightweight and interpretable neural modeling of an audio distortion effect using hyper-conditioned differentiable biquads.” International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Toronto, Canada. June 6–11, 2021

  • Shahan Nercessian, “Improved zero-shot voice conversion using explicit conditioning signals”. Proceedings of Interspeech 2020,Shanghai, China, October 25–29, 2020.

  • Shahan Nercessian, “Zero-shot singing voice conversion.” Proceedings of the 21st International Society for Music information Retrieval (ISMIR) Conference. Montreal, Canada, October 11–15, 2020

  • Shahan Nercessian. “Neural parametric equalizer matching using differentiable biquads”. Proceedings of the International Conference on Digital Audio Effects (DAFx-20). Vienna, Austria, September 8–12, 2020

  • Andy Sarroff & Roth Michaels. “Blind arbitrary reverb matching.” Proceedings of the International Conference on Digital Audio Effects (DAFx-20). Vienna, Austria September 8–12, 2020

  • Kurt James Werner, “Energy-preserving time-varying Schroeder allpass filters”. Proceedings of the International Conference on Digital Audio Effects (DAFx-20) Vienna, Austria. September 8–12, 2020.

  • Kurt James Werner & Russell McClellan. Moog ladder filter generalizations based on state variable filters. Proceedings of the International Conference on Digital Audio Effects (DAFx-20). Vienna, Austria. September 8–12, 2020.

  • Shahan Nercessian. “Voice conversion using phonetic information and WaveRNN.” Speech and Audio in the Northeast (SANE) New York, NY October 24, 2019.

  • Shahan Nercessian & Alexey Lukin, “Speech dereverberation using recurrent neural networks”. Proceedings of the 22nd International Conference on Digital Audio Effects (DAFx-19). Birmingham, UK September 2–4, 2019.

  • Gordon Wichern & Alexey Lukin. Removing lavalier microphone rustle with recurrent neural networks.” Proceedings of the International Conference on Digital Audio Effects (DAFx-18). Aveiro, Portugal. September 4–8, 2018.

  • James McClellan, Gordon Wichern, Hannah Robertson, Aaron Wishnick, Alexey Lukin, Matthew Hines, & Nicholas LaPenn “Systems and methods for identifying and remediating sound masking.” US patent. US20200403592A1. Pending. June 16, 2020

  • Todd Baker, Alexey Lukin, Jonathan Bailey, & Matthew Campbell, “Identifying and addressing noise in an audio signal.” US patent US20200202882A1 Pending, March 4, 2020.

  • Jonathan Bailey, Todd Baker, Brett Bunting, Mark Ethier, Matt Fuerch. “Audio control system and related methods.” US patent. US20190073190A1. Active through January 29, 2038.

  • James McClellan, Gordon Wichern, Aaron Wishnick, Alexey Lukin, & Matthew Hines Systems and methods for automatically generating enhanced audio output. US patent US10635389B2. Active through May 24, 2038.

  • Todd Baker, Brett Bunting, Axel Hartmann, Taylor Jordan, Damon Lemmon, Jonah Petri, & Giacomo Strollo, “Audio controller”. US patent, USD847788S1, Active through May 7, 2034.

  • Aaron Wishnick, “Audio dynamic range adjustment system and method.” US patent US9350312B1 . Active through September 20, 2034 .

  • Alexey Lukin, “Audio limiter system and method.” US patent. US9225310B1. Active through June 27, 2034.

  • Jay LeBoeuf, Stephen Pope, “Automatic labeling and control of audio algorithms by audio recognition” US patent. US9031243B2. Active through October 9, 2031.

  • Art Gillespie, Brendan Regan, & Jeremy Todd, “Sound sequencing system and method.” US patent, US9076264B1. Active through October, 15, 2031.

iZotope Logo
iZotope Logo

We make innovative audio products that inspire and enable people to be creative.