World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
33
Citations
9566
World Ranking
12384
National Ranking
5018

Overview

Daniel Garcia-Romero is affiliated with Johns Hopkins University in the United States. Their research is primarily situated within the field of computer science, with specific emphasis on artificial intelligence and signal processing. Their work intersects several areas related to speech and audio technologies.

The main topics explored by Garcia-Romero include:

  • Speech Recognition and Synthesis
  • Music and Audio Processing
  • Speech and Audio Processing
  • Natural Language Processing Techniques
  • Adversarial Robustness in Machine Learning

Garcia-Romero has authored and contributed to multiple publications, with notable papers including:

  • Recent Developments on ESPnet Toolkit Boosted by Conformer, 2020, arXiv (Cornell University)
  • The VoxCeleb Speaker Recognition Challenge: A Retrospective, 2024, IEEE/ACM Transactions on Audio Speech and Language Processing
  • VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge, 2023, arXiv (Cornell University)
  • Directed speech separation for automatic speech recognition of long form conversational speech, 2022, Interspeech 2022
  • VoxWatch: An open-set speaker recognition benchmark on VoxCeleb, 2023, arXiv (Cornell University)

The frequent co-authors collaborating with Garcia-Romero include:

  • Katrin Kirchhoff
  • Sundararajan Srinivasan
  • Jaesung Huh
  • Joon Son Chung
  • Arsha Nagrani

Garcia-Romero's research findings have been disseminated predominantly through the following venues:

  • arXiv (Cornell University)
  • IEEE/ACM Transactions on Audio Speech and Language Processing
  • Interspeech 2022

Best Publications

  • X-Vectors: Robust DNN Embeddings for Speaker Recognition

    David Snyder;Daniel Garcia-Romero;Gregory Sell;Daniel Povey

  • Analysis of i-vector Length Normalization in Speaker Recognition Systems.

    Daniel Garcia-Romero;Carol Y. Espy-Wilson

  • Deep Neural Network Embeddings for Text-Independent Speaker Verification.

    David Snyder;Daniel Garcia-Romero;Daniel Povey;Sanjeev Khudanpur

  • Deep neural network-based speaker embeddings for end-to-end speaker verification

    David Snyder;Pegah Ghahremani;Daniel Povey;Daniel Garcia-Romero

  • Speaker Recognition for Multi-speaker Conversations Using X-vectors

    David Snyder;Daniel Garcia-Romero;Gregory Sell;Alan McCree

  • Speaker diarization using deep neural network embeddings

    Daniel Garcia-Romero;David Snyder;Gregory Sell;Daniel Povey

  • Spoken Language Recognition using X-vectors.

    David Snyder;Daniel Garcia-Romero;Alan McCree;Gregory Sell

  • Speaker diarization with plda i-vector scoring and unsupervised calibration

    Gregory Sell;Daniel Garcia-Romero

  • Diarization is hard: Some experiences and lessons learned for the JHU team in the inaugural dihard challenge

    Gregory Sell;David Snyder;Alan McCree;Daniel Garcia-Romero

  • Recent Developments on Espnet Toolkit Boosted By Conformer

    Pengcheng Guo;Florian Boyer;Xuankai Chang;Tomoki Hayashi

  • Linear versus mel frequency cepstral coefficients for speaker recognition

    Xinhui Zhou;Daniel Garcia-Romero;Ramani Duraiswami;Carol Espy-Wilson

  • Time delay deep neural network-based universal background models for speaker recognition

    David Snyder;Daniel Garcia-Romero;Daniel Povey

  • A comparative evaluation of fusion strategies for multimodal biometric verification

    J. Fierrez-Aguilar;J. Ortega-Garcia;D. Garcia-Romero;J. Gonzalez-Rodriguez

  • Supervised domain adaptation for I-vector based speaker recognition

    Daniel Garcia-Romero;Alan McCree

  • Multicondition training of Gaussian PLDA models in i-vector space for noise and reverberation robust speaker recognition

    Daniel Garcia-Romero;Xinhui Zhou;Carol Y. Espy-Wilson

  • UNSUPERVISED DOMAIN ADAPTATION FOR I-VECTOR SPEAKER RECOGNITION

    Niko Brummer;Alan McCree;Stephen Shum;Daniel Garcia-Romero

  • State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and Speakers in the Wild evaluations

    Jesús Villalba;Nanxin Chen;David Snyder;Daniel Garcia-Romero

  • Adapted user-dependent multimodal biometric authentication exploiting general information

    Julian Fierrez-Aguilar;Daniel Garcia-Romero;Javier Ortega-Garcia;Joaquin Gonzalez-Rodriguez

  • The NIST 2014 Speaker Recognition i-vector Machine Learning Challenge.

    Alan McCree;Douglas A. Reynolds;Daniel Garcia-Romero;Tomi Kinnunen

  • Automatic acquisition device identification from speech recordings

    Daniel Garcia-Romero;Carol Y. Espy-Wilson

  • Linear versus Mel Frequency Cepstral Coefficients for Speaker Recognition (Author's Manuscript)

    Xinhui Zhou;Daniel Garcia-Romero;Ramani Duraiswami;Carol Espy-Wilson

Frequent Co-Authors

Alan V. McCree
Alan V. McCree Johns Hopkins University
Daniel Povey
Daniel Povey Xiaomi (China)
Javier Ortega-Garcia
Javier Ortega-Garcia Autonomous University of Madrid
Joaquin Gonzalez-Rodriguez
Joaquin Gonzalez-Rodriguez Autonomous University of Madrid
Sanjeev Khudanpur
Sanjeev Khudanpur Johns Hopkins University
Ramani Duraiswami
Ramani Duraiswami University of Maryland, College Park
Najim Dehak
Najim Dehak Johns Hopkins University
George R. Doddington
George R. Doddington Texas Instruments (United States)
Shihab A. Shamma
Shihab A. Shamma University of Maryland, College Park

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

Pursuing a Computer Science degree in the USA opens doors to a wide range of career options, especially with the growth of online education. Many college with low gpa opportunities make it possible for students from various academic backgrounds to begin their journey in tech fields.

For those seeking rapid entry into the workforce, choosing a fastest computer science degree can help you graduate sooner and start building your career quickly. These accelerated programs combine flexibility with rigorous coursework, making them ideal for motivated learners.

Additionally, tech-related knowledge pairs well with other growing sectors, such as environmental science. If you’re interested in sustainability, you might explore "what can you do with an environmental studies degree" (what can you do with an environmental studies degree) to see crossover roles in data analysis, project management, and policy development.

For hands-on, practical roles, consider an environmental engineering degree online. This could prepare you for high-demand positions working on technology-driven solutions to environmental challenges, enhancing your career flexibility and impact.

Best Scientists Citing Daniel Garcia-Romero

Trending Scientists