Elshamy Engineering - Dr.-Ing., Freelancer IT-Beratung aus Braunschweig

Expertise

Der Schwerpunkt meiner Expertise liegt in den folgenden Bereichen. Sie ist jedoch nicht ausschließlich darauf beschränkt.

Datenanalyse
Digitale Signalverarbeitung
(z.B.: Störgeräuschreduktion, Echokompensation, Automatische Spracherkennung)
IT-Administration (Linux, Windows)
Lektorat von wissenschaftlichen Arbeiten
(z.B.: Bachelorarbeit, Masterarbeit, Dissertation, Publikation)
Machine Learning
Softwareentwicklung
Webentwicklung

Eine Übersicht über meine wissenschaftlichen Publikationen und Patenten befindet sich hier.Aus Datenschutzgründen schicke ich ein detailliertes Profil mit ausführlichem Portfolio gerne auf Anfrage an mail@elshamy.engineering.

Publikationen

[1] Marc-Andre Jung, Samy Elshamy, and Tim Fingscheidt, "An Automotive Wideband Stereo Acoustic Echo Canceler Using Frequency-Domain Adaptive Filtering" in Proc. of 22nd European Signal Processing Conference, Lisbon, Portugal, Sept. 2014, pp. 1452-1456.[2] Samy Elshamy, Nilesh Madhu, Wouter J. Tirry, and Tim Fingscheidt, "An Iterative Speech Model-Based A Priori SNR Estimator" in Proc. of Interspeech, Dresden, Germany, Sept. 2015, pp. 1740-1744.[3] Samy Elshamy, Nilesh Madhu, Wouter Tirry, and Tim Fingscheidt, "Instantaneous A Priori SNR Estimation by Cepstral Excitation Manipulation" IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 8, pp. 1592-1605, Aug. 2017.[4] ----, "Two-Stage Speech Enhancement with Manipulation of the Cepstral Excitation" in Proc. of HSCMA, San Francisco, CA, USA, Mar. 2017, pp. 106-110.[5] ----, "DNN-Supported Speech Enhancement With Cepstral Estimation of Both Excitation and Envelope" IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 26, no. 12, pp. 2460-2474, Dec. 2018.[6] ----, "A Priori SNR Computation for Speech Enhancement Based on Cepstral Envelope Estimation" in Proc. of IWAENC, Tokyo, Japan, Sept. 2018, pp. 531-535.[7] Ziyue Zhao, Samy Elshamy, Huijun Liu, and Tim Fingscheidt, "A CNN Postprocessor to Enhance Coded Speech" in Proc. of IWAENC, Tokyo, Japan, Sept. 2018, pp. 406-410.[8] Ziyi Xu, Samy Elshamy, and Tim Fingscheidt, "A Priori SNR Estimation Using Discriminative Non-Negative Matrix Factorization" in Proc. of ICASSP, Calgary, AB, Canada, Apr. 2018, pp. 661-665.[9] Samy Elshamy and Tim Fingscheidt, "DNN-Based Cepstral Excitation Manipulation for Speech Enhancement" IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 27, no. 11, pp. 1803-1814, Nov. 2019.[10] ----, "Improvement of Speech Residuals for Speech Enhancement" in Proc. of WASPAA, New Paltz, NY, USA, Oct. 2019, pp. 219-223.[11] Ziyue Zhao, Samy Elshamy, and Tim Fingscheidt, "A Perceptual Weighting Filter Loss for DNN Training in Speech Enhancement" in Proc. of WASPAA, New Paltz, NY, USA, Oct. 2019, pp. 229-233.[12] Ziyi Xu, Samy Elshamy, and Tim Fingscheidt, "Using Separate Losses for Speech and Noise in Mask-Based Speech Enhancement" in Proc. of ICASSP, Barcelona, Spain, May 2020, pp. 7519-7523.[13] Patrick Meyer, Samy Elshamy, and Tim Fingscheidt, "A Multichannel Kalman-Based Wiener Filter Approach for Speaker Interference Reduction in Meetings" in Proc. of ICASSP, Barcelona, Spain, May 2020, pp. 451-455.[14] Samy Elshamy, "Speech Enhancement Exploiting the Source-Filter Model" Ph.D. dissertation, Braunschweig, 2020, Dissertation Technische Universität Braunschweig, 2020. [Online]. Available: https://publikationsserver.tu-braunschweig.de/receive/dbbs_mods_00069305[15] Patrick Meyer, Samy Elshamy, and Tim Fingscheidt, "Multichannel Speaker Interference Reduction Using Frequency Domain Adaptive Filtering" EURASIP Journal on Audio, Speech, and Music Processing, no. 14, Nov. 2020.[16] Patrick Meyer, Samy Elshamy, Jan Franzen, and Tim Fingscheidt, "Multichannel Acoustic Echo Cancellation Applied to Microphone Leakage Reduction in Meetings" in Proc. of EUSIPCO, Amsterdam, Netherlands, Jan. 2021, pp. 201-205.[17] Ziyi Xu, Samy Elshamy, Ziyue Zhao, and Tim Fingscheidt, "Components Loss for Neural Networks in Mask-Based Speech Enhancement" EURASIP Journal on Audio, Speech, and Music Processing, no. 24, July 2021.

Patente

[1] S. Elshamy, T. Fingscheidt, N. Madhu, and W. Tirry, "SIGNAL PROCESSOR" Chinese Patent CN107 437 421A, Dec. 05, 2017.[2] ----, "SIGNAL PROCESSOR" U.S. Patent US10 297 272B2, May 21, 2019.[3] ----, "A SIGNAL PROCESSOR" European Patent EP3 242 295B1, Sept. 20, 2019.