World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
53
Citations
15047
World Ranking
4726
National Ranking
2197

Overview

John R. Hershey is a researcher affiliated with Google in the United States, specializing in computer science with a focus on signal processing and artificial intelligence. Their body of work primarily addresses topics related to speech and audio processing, speech recognition and synthesis, and music and audio processing.

Their research contributions encompass a variety of topics, including:

  • Speech and Audio Processing
  • Speech Recognition and Synthesis
  • Music and Audio Processing
  • Hearing Loss and Rehabilitation
  • Advanced Adaptive Filtering Techniques
  • Phonetics and Phonology Research
  • Animal Vocal Communication and Behavior

Hershey has published extensively in venues such as:

  • arXiv (Cornell University)
  • Zenodo (CERN European Organization for Nuclear Research)
  • ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Interspeech 2022
  • OPAL (Open@LaTrobe) (La Trobe University)

Among their recent publications are:

  • Unsupervised Sound Separation Using Mixture Invariant Training, 2020, arXiv (Cornell University)
  • Improving Bird Classification with Unsupervised Sound Separation, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes, 2020, arXiv (Cornell University)
  • Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds, 2020, arXiv (Cornell University)
  • Distance-Based Sound Separation, 2022, Interspeech 2022

Hershey has collaborated frequently with several researchers, including:

  • Scott Wisdom
  • Hakan Erdoğan
  • Efthymios Tzinis
  • Shinji Watanabe
  • Nicolas Turpault

Their research predominantly falls within the main field of computer science, with significant contributions to signal processing and artificial intelligence. The subfields also include cognitive neuroscience, computational mechanics, and computer vision and pattern recognition.

Best Publications

  • Deep clustering: Discriminative embeddings for segmentation and separation

    John R. Hershey;Zhuo Chen;Jonathan Le Roux;Shinji Watanabe

  • Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models

    J. R. Hershey;P. A. Olsen

  • SDR – Half-baked or Well Done?

    Jonathan Le Roux;Scott Wisdom;Hakan Erdogan;John R. Hershey

  • Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

    Shinji Watanabe;Takaaki Hori;Suyoun Kim;John R. Hershey

  • Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks

    Hakan Erdogan;John R. Hershey;Shinji Watanabe;Jonathan Le Roux

  • Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR

    Felix Weninger;Hakan Erdogan;Shinji Watanabe;Emmanuel Vincent

  • Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures

    John R. Hershey;Jonathan Le Roux;Felix Weninger

  • Attention-Based Multimodal Fusion for Video Description

    Chiori Hori;Takaaki Hori;Teng-Yok Lee;Ziming Zhang

  • Single-Channel Multi-Speaker Separation using Deep Clustering

    Yusuf Ziya Isik;Yusuf Ziya Isik;Jonathan Le Roux;Zhuo Chen;Zhuo Chen;Shinji Watanabe

  • VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

    Hannah Raphaelle Muckenhirn;Ignacio Lopez Moreno;John Hershey;Kevin Wilson

  • Audio Vision: Using Audio-Visual Synchrony to Locate Sounds

    John R. Hershey;Javier R. Movellan

  • Improved MVDR beamforming using single-channel mask prediction networks

    Hakan Erdogan;John R. Hershey;Shinji Watanabe;Michael I. Mandel

  • Discriminatively trained recurrent neural networks for single-channel speech separation

    Felix Weninger;John R. Hershey;Jonathan Le Roux;Bjorn Schuller

  • Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation

    Zhong-Qiu Wang;Jonathan Le Roux;John R. Hershey

  • Full-capacity unitary recurrent neural networks

    Scott Wisdom;Thomas Powers;John R. Hershey;Jonathan Le Roux

  • Monaural speech separation and recognition challenge

    Martin Cooke;John R. Hershey;Steven J. Rennie

  • Super-human multi-talker speech recognition: A graphical modeling approach

    John R. Hershey;Steven J. Rennie;Peder A. Olsen;Trausti T. Kristjansson

  • Deep beamforming networks for multi-channel speech recognition

    Xiong Xiao;Shinji Watanabe;Hakan Erdogan;Liang Lu

  • Alternative Objective Functions for Deep Clustering

    Zhong-Qiu Wang;Jonathan Le Roux;John R. Hershey

  • Deep clustering and conventional networks for music separation: Stronger together

    Yi Luo;Zhuo Chen;John R. Hershey;Jonathan Le Roux

Frequent Co-Authors

Shinji Watanabe
Shinji Watanabe Carnegie Mellon University
Jonathan Le Roux
Jonathan Le Roux Mitsubishi Electric (United States)
Hakan Erdogan
Hakan Erdogan Google (United States)
Felix Weninger
Felix Weninger Nuance Communications (United States)
Daniel P. W. Ellis
Daniel P. W. Ellis Google (United States)
Justin Salamon
Justin Salamon Adobe Systems (United States)
Javier R. Movellan
Javier R. Movellan University of California, San Diego
Aren Jansen
Aren Jansen Google (United States)
Emmanuel Vincent
Emmanuel Vincent University of Lorraine

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens doors to a wide range of flexible online study options. For those just starting, there are associate degrees that offer foundational skills and quick entry into tech careers. These programs can be a great stepping stone toward more advanced study or direct workforce entry.

If you’re interested in affordable and accessible learning, consider enrolling in fully online accredited colleges. These institutions provide recognized credentials and the convenience of studying from anywhere, making them ideal for working professionals or those balancing other responsibilities.

Online education has also expanded to specialized areas. For those passionate about video games, game development degree pathways let you build job-ready skills for the gaming industry—all through remote learning.

Career advancement is also possible with higher-level online programs, such as the online ed degrees, which are designed for those aiming for leadership and teaching roles. No matter your career goal, online programs in computer science and related fields can help you achieve it at your own pace.

Best Scientists Citing John R. Hershey

Trending Scientists

Recently Published Articles