Edge Rewrite
pun Source code View original
Jump to content

Draft:Phillip De Leon

From Wikipedia, the free encyclopedia


Phillip L. De Leon
Born
San Antonio, Texas, U.S.
Alma mater
Known forResearch on the vulnerability of speaker verification systems to synthetic speech; time–frequency signal analysis
Awards
  • Paul W. and Valerie Klipsch Distinguished Professorship (2015–2022)
  • John and Tome Nakayama Professorship (2012–2015)
  • Fulbright Faculty Scholar Award (2008)
Scientific career
FieldsDigital signal processing, speech processing, speaker verification, machine learning
Institutions

Phillip L. De Leon is an American electrical engineer and academic administrator who is associate vice chancellor for research and chief research officer at the University of Colorado Denver, where he is also a professor of electrical engineering.[1][2] He was previously a professor in the Klipsch School of Electrical and Computer Engineering at New Mexico State University (NMSU), where he held the Paul W. and Valerie Klipsch Distinguished Professorship and served as associate vice president for research and chief science officer.[1][3][4]

De Leon's research is in digital signal processing, with emphasis on speech processing, time–frequency analysis, and machine learning. He is known in particular for early work quantifying the vulnerability of automatic speaker verification systems to synthetic speech and for methods to detect such attacks, a line of research that anticipated later interest in deepfake audio detection.[5][6]

Early life and education

[edit]

De Leon is a native of San Antonio, Texas.[7] He first encountered university research through summer STEM enrichment programs for minority students at the University of Texas at San Antonio and the Massachusetts Institute of Technology while in high school.[8] He earned a Bachelor of Science in electrical engineering (1989) and a Bachelor of Arts in mathematics (1990) from the University of Texas at Austin Supported by a doctoral fellowship from AT&T Bell Laboratories, he received the Master of Science and Ph.D. degrees in electrical engineering from the University of Colorado Boulder, completing the doctorate in 1995.[8][9][10] His early publications on subband adaptive filtering and acoustic echo cancellation were co-authored with Delores Etter.[11]

Career

[edit]

De Leon joined the faculty of New Mexico State University in 1996 and remained there until 2022.[3] He directed the Advanced Speech and Audio Processing Laboratory and served as associate department head in the Klipsch School of Electrical and Computer Engineering.[10] He held the John and Tome Nakayama Professorship in Engineering for Teaching Excellence from 2012 to 2015 — NMSU's first endowed professorship in teaching — and the Paul W. and Valerie Klipsch Distinguished Professorship from 2015 to 2022.[3][4]

From 2016 to 2019 he was associate dean of research in the NMSU College of Engineering, a period in which the college reported growth in research expenditures and proposal success.[12][13] He was subsequently appointed associate vice president for research and later chief science officer for the university.[12][1]

In March 2022, following a national search, De Leon was named associate vice chancellor for research at the University of Colorado Denver, beginning in August 2022.[1] In that role he oversees the campus research and creative activities enterprise, including research and proposal development, seed funding programs, and the university's Grand Challenges initiative.[8]

International appointments

[edit]

De Leon has held visiting appointments in the Department of Computer Science at University College Cork, Ireland (2002 and 2022); the Multimedia Communications Department at EURECOM in France (2016); and the Signal and Image Processing Department at Telecom ParisTech (2016).[14] In 2008 he was a Fulbright Faculty Scholar at the Institute of Communications and Radio-Frequency Engineering of the Vienna University of Technology, Austria.[14][10] He was a faculty fellow at Sandia National Laboratories from 2016 to 2023.[14]

Research

[edit]

Speaker verification and synthetic speech

[edit]

Beginning around 2010, De Leon and collaborators including Junichi Yamagishi, Michael Pucher, Inma Hernáez, and Ibon Saratxaga published a series of studies showing that hidden Markov model–based speech synthesizers adapted to a target speaker could defeat state-of-the-art automatic speaker verification systems at high rates, and proposed countermeasures based on relative phase shift and other acoustic features.[15][16][5] The resulting 2012 paper in the IEEE Transactions on Audio, Speech, and Language Processing is his most cited work.[17]

He was a co-author of the 2016 study that introduced an initial public database and comparison of countermeasures for anti-spoofing in text-independent speaker verification,[18] and co-edited a 2017 special issue of the IEEE Journal of Selected Topics in Signal Processing on spoofing and countermeasures for automatic speaker verification.[6] He also contributed a chapter on speaker recognition anti-spoofing to Springer's Handbook of Biometric Anti-Spoofing.[19]

Time–frequency analysis and other work

[edit]

With Steven Sandoval, De Leon developed the "instantaneous spectrum," a framework that recasts a range of time–frequency representations — including the short-time Fourier transform and its synchrosqueezed variant — in terms of instantaneous amplitude and instantaneous frequency.[20][21] Other research has addressed speaker identification under reverberation and packet loss, low bit-rate speech coding through quantization of mel-frequency cepstral coefficients, radio-frequency channel modeling for wireless networks on the Martian surface, classification of power-system disturbances from phasor measurement unit data, and machine-learning classification of falls risk in older adults from smartphone gait data.[22][23][24]

More recently, working with Utz Roedig and colleagues, he has studied spoofing detection for personal voice assistants and the limitations of watermarking for AI-generated speech.[25][26]

Awards and honors

[edit]

Selected publications

[edit]
  • De Leon, Phillip L.; Pucher, Michael; Yamagishi, Junichi; Hernaez, Inma; Saratxaga, Ibon (2012). "Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech". IEEE Transactions on Audio, Speech, and Language Processing. 20 (8): 2280–2290. doi:10.1109/TASL.2012.2201472.
  • Wu, Zhizheng; De Leon, Phillip L.; et al. (2016). "Anti-Spoofing for Text-Independent Speaker Verification: An Initial Database, Comparison of Countermeasures, and Human Performance". IEEE/ACM Transactions on Audio, Speech, and Language Processing. 24 (4): 768–783. doi:10.1109/TASLP.2016.2526653.
  • Sandoval, Steven; De Leon, Phillip L. (2018). "The Instantaneous Spectrum: A General Framework for Time-Frequency Analysis". IEEE Transactions on Signal Processing. 66 (21): 5679–5693. doi:10.1109/TSP.2018.2869121.
  • Apsingekar, Vijendra Raj; De Leon, Phillip L. (2009). "Speaker Model Clustering for Efficient Speaker Identification in Large Population Applications". IEEE Transactions on Audio, Speech, and Language Processing. 17 (4): 848–853. doi:10.1109/TASL.2008.2010882.
  • Martinez, Matthew; De Leon, Phillip L. (2020). "Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning". IEEE Journal of Biomedical and Health Informatics. 24 (1): 144–150. doi:10.1109/JBHI.2019.2906499.

References

[edit]
  1. 1 2 3 4 "New Mexico State University Chief Science Officer Phillip DeLeon Named CU Denver's AVC for Research". University of Colorado Denver. March 29, 2022.
  2. ↑ "Electrical Engineering People — Phillip De Leon". University of Colorado Denver College of Engineering, Design and Computing.
  3. 1 2 3 4 5 6 "Academy of Electrical and Computer Engineering — Overview". Klipsch School of Electrical and Computer Engineering, New Mexico State University.
  4. 1 2 "Endowed Chairs and Professorships" (PDF). New Mexico State University College of Engineering.
  5. 1 2 De Leon, P. L.; Pucher, M.; Yamagishi, J.; Hernaez, I.; Saratxaga, I. (2012). "Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech". IEEE Transactions on Audio, Speech, and Language Processing. 20 (8): 2280–2290. doi:10.1109/TASL.2012.2201472.
  6. 1 2 Yamagishi, J.; Kinnunen, T. H.; Evans, N.; De Leon, P.; Trancoso, I. (2017). "Introduction to the Issue on Spoofing and Countermeasures for Automatic Speaker Verification". IEEE Journal of Selected Topics in Signal Processing. 11 (4): 585–587. doi:10.1109/JSTSP.2017.2698143.
  7. ↑ "Biography". phillip-deleon.com. Retrieved July 24, 2026.
  8. 1 2 3 "Five questions for Phillip De Leon". CU Connections. University of Colorado. November 20, 2024.
  9. ↑ "Phillip DeLeon". Coloradan Alumni Magazine. University of Colorado Boulder.
  10. 1 2 3 4 "Author biography: Phillip L. De Leon". IEEE Transactions on Audio, Speech, and Language Processing. 20 (8): 2290. 2012. doi:10.1109/TASL.2012.2201472.
  11. ↑ De Leon, P. L.; Etter, D. M. (1995). "Experimental results with increased bandwidth analysis filters in oversampled subband acoustic echo cancelers". IEEE Signal Processing Letters. 2 (1): 1–3. doi:10.1109/97.365516.
  12. 1 2 "NMSU College of Engineering highlights faculty research successes". New Mexico State University. October 25, 2019.
  13. ↑ "Phillip De Leon". Coloradan Alumni Magazine. University of Colorado Boulder.
  14. 1 2 3 4 5 6 "Phillip De Leon — Professor & Chief Research Officer". Retrieved July 24, 2026.
  15. ↑ De Leon, P. L.; Pucher, M.; Yamagishi, J. (2010). "Evaluation of the Vulnerability of Speaker Verification to Synthetic Speech". Proc. Odyssey: The Speaker and Language Recognition Workshop. pp. 151–158.
  16. ↑ De Leon, P. L.; Hernaez, I.; Saratxaga, I.; Pucher, M.; Yamagishi, J. (2011). "Detection of Synthetic Speech for the Problem of Imposture". Proc. IEEE ICASSP. pp. 4844–4847. doi:10.1109/ICASSP.2011.5947440.
  17. ↑ "Phillip De Leon". Google Scholar. Retrieved July 24, 2026.
  18. ↑ Wu, Z.; De Leon, P. L.; et al. (2016). "Anti-Spoofing for Text-Independent Speaker Verification". IEEE/ACM Transactions on Audio, Speech, and Language Processing. 24 (4): 768–783. doi:10.1109/TASLP.2016.2526653.
  19. ↑ Evans, N.; Kinnunen, T.; Yamagishi, J.; Wu, Z.; Alegre, F.; De Leon, P. (2014). "Speaker Recognition Anti-Spoofing". In Marcel, S.; Nixon, M.; Li, S. Z. (eds.). Handbook of Biometric Anti-Spoofing. Springer. doi:10.1007/978-1-4471-6524-8_7.
  20. ↑ Sandoval, S.; De Leon, P. L. (2018). "The Instantaneous Spectrum: A General Framework for Time-Frequency Analysis". IEEE Transactions on Signal Processing. 66 (21): 5679–5693. doi:10.1109/TSP.2018.2869121.
  21. ↑ Sandoval, S.; De Leon, P. L. (2022). "Recasting the (Synchrosqueezed) Short-Time Fourier Transform as an Instantaneous Spectrum". Entropy. 24 (4). doi:10.3390/e24040518.
  22. ↑ Martinez, M.; De Leon, P. L. (2020). "Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning". IEEE Journal of Biomedical and Health Informatics. 24 (1): 144–150. doi:10.1109/JBHI.2019.2906499.
  23. ↑ Boucheron, L. E.; De Leon, P. L.; Sandoval, S. (2012). "Low Bit-Rate Speech Coding through Quantization of Mel-Frequency Cepstral Coefficients". IEEE Transactions on Audio, Speech, and Language Processing. 20 (2): 610–619. doi:10.1109/TASL.2011.2162407.
  24. ↑ Chukkala, V.; De Leon, P.; Horan, S.; Velusamy, V. (2005). "Radio Frequency Channel Modeling for Proximity Networks on the Martian Surface". Computer Networks. 47 (5): 751–763. doi:10.1016/j.comnet.2004.08.011.
  25. ↑ Sankar, A.; De Leon, P. L.; Roedig, U. (2023). "Spoofing Detection for Personal Voice Assistants". Proc. International Workshop on Security and Privacy of Sensing Systems. doi:10.1145/3628356.3630114.
  26. ↑ Faziludeen, S.; Sankar, A.; De Leon, P. L.; Roedig, U. (2025). "Limitations of Watermarking AI-Generated Speech using AudioSeal". Proc. IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications. doi:10.1109/TPS-ISA67132.2025.00029.
[edit]

Category:Living people Category:American electrical engineers Category:University of Texas at Austin alumni Category:University of Colorado Boulder alumni Category:New Mexico State University faculty Category:University of Colorado Denver faculty Category:Scientists from San Antonio Category:American academic administrators

References

[edit]
Retrieved from "https://en.wikipedia.org/w/index.php?title=Draft:Phillip_De_Leon&oldid=1366365976"