World's Best Scientists 2026 revealed!

Overview

Hagen Soltau is a researcher affiliated with Google in the United States. Their primary field of study is Computer Science, with a particular focus on subfields such as Artificial Intelligence, Molecular Biology, Computer Vision and Pattern Recognition, Information Systems, and Physiology.

The scientist's research covers various topics, including:

  • Topic Modeling
  • Natural Language Processing Techniques
  • Speech Recognition and Synthesis
  • Speech and dialogue systems
  • Biomedical Text Mining and Ontologies
  • Multimodal Machine Learning Applications
  • Advanced Text Analysis Techniques

Hagen Soltau has published extensively, contributing 44 works across their main field. Their publications have appeared frequently in venues such as:

  • arXiv (Cornell University)
  • Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • Interspeech 2022
  • IEEE Transactions on Audio Speech and Language Processing

Recent publications include:

  • Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages, 2023, arXiv (Cornell University)
  • The Medical Scribe: Corpus Development and Model Performance Analyses, 2020, arXiv (Cornell University)
  • Unsupervised Slot Schema Induction for Task-oriented Dialog, 2022, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • Word-Level Confidence Estimation for RNN Transducers, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
  • Efficient Adapters for Giant Speech Models, 2023, arXiv (Cornell University)

Collaborations have been an integral part of Hagen Soltau's research activity. Frequent coauthors include Izhak Shafran, Mingqiu Wang, Laurent El Shafey, Yuan Cao, and Dian Yu. The number of publications with these collaborators ranges from 5 to 18, reflecting ongoing partnerships in diverse projects related to speech and language processing.

Best Publications

  • Deep Convolutional Neural Networks for Large-scale Speech Tasks

    Tara N. Sainath;Brian Kingsbury;George Saon;Hagen Soltau

  • Speaker adaptation of neural network acoustic models using i-vectors

    George Saon;Hagen Soltau;David Nahamoo;Michael Picheny

  • fMPE: discriminatively trained features for speech recognition

    D. Povey;B. Kingsbury;L. Mangu;G. Saon

  • Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition

    Hagen Soltau;Hank Liao;Hasim Sak

  • Improvements to Deep Convolutional Neural Networks for LVCSR

    Tara N. Sainath;Brian Kingsbury;Abdel-rahman Mohamed;George E. Dahl

  • Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization.

    Brian Kingsbury;Tara N. Sainath;Hagen Soltau

  • A one-pass decoder based on polymorphic linguistic context assignment

    H. Soltau;F. Metze;C. Fugen;A. Waibel

  • Advances in automatic meeting record creation and access

    A. Waibel;M. Bett;F. Metze;K. Ries

  • Recognition of music types

    H. Soltau;T. Schultz;M. Westphal;A. Waibel

  • The IBM Attila speech recognition toolkit

    Hagen Soltau;George Saon;Brian Kingsbury

  • Advances in speech transcription at IBM under the DARPA EARS program

    S.F. Chen;B. Kingsbury;Lidia Mangu;D. Povey

  • The IBM 2004 conversational telephony system for rich transcription

    H. Soltau;B. Kingsbury;L. Mangu;D. Povey

  • Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions

    Samuel Thomas;Sriram Ganapathy;George Saon;Hagen Soltau

  • Joint training of convolutional and non-convolutional neural networks

    Hagen Soltau;George Saon;Tara N. Sainath

  • Method and system for efficient spoken term detection using confusion networks

    Brian E. D. Kingsbury;Hong-Kwang Kuo;Lidia Mangu;Hagen Soltau

  • Classifier-based system combination for spoken term detection

    Brian E. D. Kingsbury;Hong-Kwang Jeff Kuo;Lidia Luminita Mangu;Hagen Soltau

  • Joint Speech Recognition and Speaker Diarization via Sequence Transduction

    Laurent El Shafey;Hagen Soltau;Izhak Shafran

  • The IBM speech activity detection system for the DARPA RATS program.

    George Saon;Samuel Thomas;Hagen Soltau;Sriram Ganapathy

  • Improvements to the IBM speech activity detection system for the DARPA RATS program

    Samuel Thomas;George Saon;Maarten Van Segbroeck;Shrikanth S. Narayanan

  • Multilingual Speech Recognition

    Alex Waibel;Hagen Soltau;Tanja Schultz;Thomas Schaaf

Frequent Co-Authors

George Saon
George Saon IBM (United States)
Brian Kingsbury
Brian Kingsbury IBM (United States)
Florian Metze
Florian Metze Carnegie Mellon University
Alex Waibel
Alex Waibel Carnegie Mellon University
Tanja Schultz
Tanja Schultz University of Bremen
Daniel Povey
Daniel Povey Xiaomi (China)
Tara N. Sainath
Tara N. Sainath Google (United States)
Hasim Sak
Hasim Sak Google (United States)
Bhuvana Ramabhadran
Bhuvana Ramabhadran Google (United States)
Michael Picheny
Michael Picheny IBM (United States)

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 the field of Computer Science in the USA opens doors to a variety of related programs and flexible learning options. For those interested in expanding their skill set, many students consider advanced studies in fields like electrical engineering due to overlapping technical foundations. Choosing a program from one of the top online electrical engineering schools can provide a strong complementary edge to your computer science expertise.

If you’re eager to accelerate your entry into the tech workforce, pursuing quick certifications that pay well is a practical option. These certifications focus on high-demand IT skills and can significantly boost your employability in a short period.

For those considering graduate studies, the quickest cheapest masters degree pathways allow for rapid career advancement without a long time commitment or heavy financial burden. Carefully selecting in-demand disciplines is also crucial—explore what masters program should I do to align your education with the fastest growing fields and employer needs.

Best Scientists Citing Hagen Soltau

Trending Scientists

Recently Published Articles