H
Hakan Erdogan
Researcher at Google
Publications - 202
Citations - 7488
Hakan Erdogan is an academic researcher from Google. The author has contributed to research in topics: Biometrics & Speech enhancement. The author has an hindex of 36, co-authored 202 publications receiving 6022 citations. Previous affiliations of Hakan Erdogan include Mitsubishi Electric & Scientific and Technological Research Council of Turkey.
Papers
More filters
Proceedings ArticleDOI
SDR – Half-baked or Well Done?
TL;DR: The scale-invariant signal-to-distortion ratio (SI-SDR) as mentioned in this paper is a more robust measure for single-channel separation, which has been proposed in the BSS_eval toolkit.
Proceedings ArticleDOI
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
TL;DR: A phase-sensitive objective function based on the signal-to-noise ratio (SNR) of the reconstructed signal is developed, and it is shown that in experiments it yields uniformly better results in terms of signal- to-distortion ratio (SDR).
Journal ArticleDOI
Ordered subsets algorithms for transmission tomography.
Hakan Erdogan,Jeffrey A. Fessler +1 more
TL;DR: This paper introduces a simultaneous update algorithm called separable paraboloidal surrogates (SPS) that converges much faster than the transmission EM algorithm and shows that OSTR is superior to OSEM applied to the logarithm of the transmission data.
Book ChapterDOI
Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR
Felix Weninger,Hakan Erdogan,Shinji Watanabe,Emmanuel Vincent,Jonathan Le Roux,John R. Hershey,Björn Schuller +6 more
TL;DR: It is demonstrated that LSTM speech enhancement, even when used 'naively' as front-end processing, delivers competitive results on the CHiME-2 speech recognition task.
Journal ArticleDOI
Monotonic algorithms for transmission tomography
Hakan Erdogan,Jeffrey A. Fessler +1 more
TL;DR: The new algorithms are based on paraboloidal surrogate functions for the log likelihood, which lead to monotonic algorithms even for the nonconvex log likelihood that arises due to background events, such as scatter and random coincidences.