Browsing by Author "Zhang, C."
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
Item Anti-Spoofing System: An Investigation of Measures to Detect Synthetic and Human Speech(International Speech and Communication Association) Misra, A.; Ranjan, S.; Zhang, C.; Hansen, John H. L.; 19968651 (Hansen, JHL); Hansen, John H. L.Automatic Speaker Verification (ASV) systems are prone to spoofing attacks of various kinds. In this study, we explore the effects of different features and spoofing algorithms on a state-of-the-art i-vector speaker verification system. Our study is based on the standard dataset and evaluation protocols released as part of the ASVspoof 2015 challenge. We compare how different features perform while detecting both genuine and spoofed speech. We observe that features that contain phase information (Modified Group Delay based features) are better in detecting synthetic speech, and give comparable performance when compared to standard MFCCs. We report an anti-spoofing system that performs well both on known as well as unknown spoofing attacks.Item I-Vector Based Physical Task Stress Detection with Different Fusion Strategies(International Speech and Communication Association) Zhang, C.; Liu, G.; Yu, C.; Hansen, John H. L.; 19968651 (Hansen, JHL); Zhang, C.; Liu, G.; Yu, C.; Hansen, John H. L.It is common for subjects to produce speech while performing a physical task where speech technology may be used. Variabilities are introduced to speech since physical task can influence human speech production. These variabilities degrade the performance of most speech systems. It is vital to detect speech under physical stress variabilities for subsequent algorithm processsing. This study presents a method for detecting physical task stress from speech. Inspired by the fact that i-vectors can generally model total factors from speech, a state-of-the-art ivector framework is investigated with MFCCs and our previously formulated TEO-CB-Auto-Env features for neutral/physical task stress detection. Since MFCCs are derived from a linear speech production model and TEO-CB-Auto-Env features employ a nonlinear operator, these two features are believed to have complementary effects on physical task stress detection. Two alternative fusion strategies (feature-level and score-level fusion) are investigated to validate this hypothesis. Experiments over the UT-Scope Physical Corpus demonstrate that a relative accuracy gain of 2.68% is obtained when fusing different feature based i-vectors. An additional relative performance boost with of 6.52% in accuracy is achieved using score level fusion.Item Three-Dimensionally Ordered Macro-/Mesoporous Ni as a Highly Efficient Electrocatalyst for the Hydrogen Evolution Reaction(Royal Society of Chemistry, 2015-04-13) Sun, T.; Zhang, C.; Chen, J.; Yan, Y.; Zakhidov, Anvar A.; Baughman, Ray H.; Xu, L.; 0000 0003 5232 4253 (Baughman, RH); 0000-0003-3983-2229 (Zakhidov, AA); Zakhidov, Anvar A.; Baughman, Ray H.Three-dimensionally (3D) ordered macro-/mesoporous (3DOM/m) Ni is fabricated by the chemical reduction deposition method using lyotropic liquid crystals (LLC) to template the mesostructure within the regular voids of a colloidal crystal (opal). The thereby achieved structural advantages of combining well-ordered bicontinuous mesopores with 3D interconnected periodic macropores, such as abundant exposed catalytically active sites, efficient mass transport, and high electrical conductivity, make this non-noble metal structure an excellent hydrogen evolution reaction (HER) electrocatalyst. The 3DOM/m Ni exhibits a low onset overpotential of 63 mV (vs. RHE) and a small Tafel slope of 52 mV per decade, as well as a long-term durability in alkaline medium. These distinct features of the 3DOM/m Ni render it a promising alternative to Pt-based HER electrocatalysts.