Oleg Rybakov

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 27

Top Topics

Speech Recognition

Structured Sparsity

Keyword Spotting

Significant Bit

Top Venues

Publications

Yandong Luo, Johan Vanderhaegen, Oleg Rybakov, Martin Kraemer, Niel Warren, Shimeng Yu
A FeFET-Based ADC Offset Robust Compute-In-Memory Architecture for Streaming Keyword Spotting (KWS). IEEE Trans. Emerg. Top. Comput. 12 (1) (2024)
Shaojin Ding, David Qiu, David Rim, Yanzhang He, Oleg Rybakov, Bo Li, Rohit Prabhavalkar, Weiran Wang, Tara N. Sainath, Zhonglin Han, Jian Li, Amir Yazdanbakhsh, Shivani Agrawal
USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models. ICASSP (2024)
Alex Agranovich, Eliya Nachmani, Oleg Rybakov, Yifan Ding, Ye Jia, Nadav Bar, Heiga Zen, Michelle Tadmor Ramanovich
SimulTron: On-Device Simultaneous Speech to Speech Translation. CoRR (2024)
Renkun Ni, Yonghui Xiao, Phoenix Meadowlark, Oleg Rybakov, Tom Goldstein, Ananda Theertha Suresh, Ignacio López-Moreno, Mingqing Chen, Rajiv Mathews
FedAQT: Accurate Quantized Training with Federated Learning. ICASSP (2024)
Oleg Rybakov, Dmitriy Serdyuk, Chengjian Zheng
USM RNN-T model weights binarization. CoRR (2024)
Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. ICML (2023)
Oleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang, Xia Zhang, Fadi Biadsy
Real time spectrogram inversion on mobile phone. INTERSPEECH (2023)
Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. CoRR (2023)
Shaojin Ding, David Qiu, David Rim, Yanzhang He, Oleg Rybakov, Bo Li, Rohit Prabhavalkar, Weiran Wang, Tara N. Sainath, Shivani Agrawal, Zhonglin Han, Jian Li, Amir Yazdanbakhsh
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models. CoRR (2023)
David Qiu, David Rim, Shaojin Ding, Oleg Rybakov, Yanzhang He
RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models. CoRR (2023)
Oleg Rybakov, Phoenix Meadowlark, Shaojin Ding, David Qiu, Jian Li, David Rim, Yanzhang He
2-bit Conformer quantization for automatic speech recognition. INTERSPEECH (2023)
Oleg Rybakov, Fadi Biadsy, Xia Zhang, Liyang Jiang, Phoenix Meadowlark, Shivani Agrawal
Streaming Parrotron for on-device speech-to-speech conversion. INTERSPEECH (2023)
Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro J. Moreno
A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization. INTERSPEECH (2022)
Shaojin Ding, Phoenix Meadowlark, Yanzhang He, Lukasz Lew, Shivani Agrawal, Oleg Rybakov
4-bit Conformer with Native Quantization Aware Training for Speech Recognition. CoRR (2022)
Oleg Rybakov, Fadi Biadsy, Xia Zhang, Liyang Jiang, Phoenix Meadowlark, Shivani Agrawal
Streaming Parrotron for on-device speech-to-speech conversion. CoRR (2022)
Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro J. Moreno
A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization. CoRR (2022)
Shaojin Ding, Phoenix Meadowlark, Yanzhang He, Lukasz Lew, Shivani Agrawal, Oleg Rybakov
4-bit Conformer with Native Quantization Aware Training for Speech Recognition. INTERSPEECH (2022)
Oleg Rybakov, Marco Tagliasacchi, Yunpeng Li, Liyang Jiang, Xia Zhang, Fadi Biadsy
Real time spectrogram inversion on mobile phone. CoRR (2022)
Yunpeng Li, Marco Tagliasacchi, Oleg Rybakov, Victor Ungureanu, Dominik Roblek
Real-Time Speech Frequency Bandwidth Extension. ICASSP (2021)
AmirAli Abdolrashidi, Lisa Wang, Shivani Agrawal, Jonathan Malmaud, Oleg Rybakov, Chas Leichner, Lukasz Lew
Pareto-Optimal Quantized ResNet Is Mostly 4-bit. CoRR (2021)
AmirAli Abdolrashidi, Lisa Wang, Shivani Agrawal, Jonathan Malmaud, Oleg Rybakov, Chas Leichner, Lukasz Lew
Pareto-Optimal Quantized ResNet Is Mostly 4-Bit. CVPR Workshops (2021)
Yunpeng Li, Marco Tagliasacchi, Oleg Rybakov, Victor Ungureanu, Dominik Roblek
Real-time Speech Frequency Bandwidth Extension. CoRR (2020)
Oleg Rybakov, Natasha Kononenko, Niranjan Subrahmanya, Mirkó Visontai, Stella Laurenzo
Streaming keyword spotting on mobile devices. CoRR (2020)
Oleg Rybakov, Natasha Kononenko, Niranjan Subrahmanya, Mirkó Visontai, Stella Laurenzo
Streaming Keyword Spotting on Mobile Devices. INTERSPEECH (2020)
Pranav Ladkat, Oleg Rybakov, Radhika Arava, Sree Hari Krishnan Parthasarathi, I-Fan Chen, Nikko Strom
Two Tiered Distributed Training Algorithm for Acoustic Modeling. INTERSPEECH (2019)
Yuriy Mishchenko, Yusuf Goren, Ming Sun, Chris Beauchene, Spyros Matsoukas, Oleg Rybakov, Shiv Naga Prasad Vitaladevuni
Low-Bit Quantization and Quantization-Aware Training for Small-Footprint Keyword Spotting. ICMLA (2019)
Oleg Rybakov, Vijai Mohan, Avishkar Misra, Scott LeGrand, Rejith Joseph, Kiuk Chung, Siddharth Singh, Qian You, Eric T. Nalisnick, Leo Dirac, Runfei Luo
The Effectiveness of a two-Layer Neural Network for Recommendations. ICLR (Workshop) (2018)