Learn More
In this letter, the pH time-frequency vocal source feature is proposed for multistyle emotion identification. A binary acoustic mask is also used to improve the emotion classification accuracy. Emotional and stress conditions from the Berlin Database of Emotional Speech (EMO-DB) and Speech under Simulated and Actual Stress (SUSAS) databases are investigated(More)
Since their introduction into surgical practice in the mid 1990s, intraoperative MRI systems have evolved into essential, routinely used tools for the surgical treatment of brain tumors in many centers. Clear delineation of the lesion, "under-the-surface" vision, and the possibility of obtaining real-time feedback on the extent of resection and the position(More)
This paper presents a speech enhancement technique for signals corrupted by nonstationary acoustic noises. The proposed approach applies the empirical mode decomposition (EMD) to the noisy speech signal and obtains a set of intrinsic mode functions (IMF). The main contribution of the proposed procedure is the adoption of the Hurst exponent in the selection(More)
A robust biometric access system for optical communications based on a speaker identification authentication is proposed in this paper. The solution also enables optical access with remote speaker identification. A set of speech features and classifiers were defined to achieve the best recognition rates. The experiments demonstrated the feasibility and(More)
This paper investigates the fusion of Mel-frequency cepstral coefficients (MFCC) and statistical pH features to improve the performance of speaker verification (SV) in non-stationary noise conditions. The α-integrated Gaussian Mixture Model (α-GMM) classifier is adopted for speaker modeling. Two different approaches are applied to reduce the(More)
This paper investigates the fusion of Mel-frequency cepstral coefficients (MFCC) and statistical pH features to improve the performance of speaker verification (SV) in non-stationary noise conditions. The α-integrated Gaussian Mixture Model ( α-GMM) classifier is adopted for speaker modeling. Two different approaches are applied to reduce the(More)
This paper introduces an adaptive noise detection method for non-stationary acoustic noisy signals. The proposed approach is based on the empirical mode decomposition (EMD) and a vector of Hurst exponent coefficients. The scheme is investigated considering real acoustic noisy signals with different non-stationarity degree and signal-to-noise ratio (SNR).(More)
  • 1