C
Chung Chien Hsu
Researcher at National Chiao Tung University
Publications - 10
Citations - 89
Chung Chien Hsu is an academic researcher from National Chiao Tung University. The author has contributed to research in topics: Non-negative matrix factorization & Bayesian probability. The author has an hindex of 6, co-authored 10 publications receiving 77 citations.
Papers
More filters
Journal ArticleDOI
Robust Voice Activity Detection Algorithm Based on Feature of Frequency Modulation of Harmonics and Its DSP Implementation
TL;DR: This paper proposes a voice activity detection (VAD) algorithm based on an energy related feature of the frequency modulation of harmonics that performs significantly better than three standard VADs, ITU-T G.729B, ETSI AMR1 and AMR2, in non-stationary noise.
Proceedings Article
Bayesian singing-voice separation
TL;DR: This paper presents a Bayesian nonnegative matrix factorization (NMF) approach to extract singing voice from background music accompaniment that performs better than various unsupervised separation algorithms in terms of the global normalized source to distortion ratio.
Journal ArticleDOI
Multiband analysis and synthesis of spectro-temporal modulations of Fourier spectrogram.
Tai-Shih Chi,Chung Chien Hsu +1 more
TL;DR: The proposed framework not only provides a similar spectro-temporal analytical process for sounds as the auditory model but also produces synthesized sounds with better quality in a timely manner, which makes proposed framework feasible to human speech recognition (HSR) applications as well.
Journal ArticleDOI
Spectro-temporal modulation energy based mask for robust speaker identification
TL;DR: Simulation results show the proposed method produces much higher speaker identification rates in all signal-to-noise ratio (SNR) conditions than the baseline system using mel-frequency cepstral coefficients.
Proceedings ArticleDOI
Layered Nonnegative Matrix Factorization for Speech Separation
TL;DR: Simulation results show the proposed LNMF outperforms the standard NMF in terms of the source-todistortion ratio (SDR), and these complicated bases contain collective information of the parts-based bases.