The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we propose a novel method for improving performance of the acoustic echo canceller (AEC) employed in the hands-free communication. The main objective is to realize an improved performance without requiring a double talk detector (DTD). The basic idea is to employ a gradient-based independent component analysis (ICA) method with a generalized Cauchy distribution-based flexible score...
In this paper, we propose a method to improve detecting the mispronunciation type of the non-native learners. In order to cope with the low-resource condition of non-native speech and the difference of native and non-native speech, the following efforts are made: 1) train acoustic model with the low-resource non-native data; 2) introduce the articulatory-based tandem feature; 3) pool auxiliary native...
This paper introduces the use of two new features for speaker identification, Residual Phase Cepstrum Coefficients (RPCC) and Glottal Flow Cepstrum Coefficients (GLFCC), to capture speaker-specific characteristics from their vocal excitation patterns. Results on a cross-lingual speaker identification task taken from the NIST 2004 SRE demonstrate that these RPCC and GLFCC features are significantly...
Scans of double-sided documents often suffer from show-through distortions, where contents of the reverse side (verso) may appear in the front-side page (recto). Several algorithms employed for show-through removal from the scanned images, are based on linear mixing models, including blind source separation (BSS), non-negative matrix factorization (NMF), and adaptive filtering. However, a recent study...
Speaker verification suffers from significant performance degradation on emotional speech. We present an adaptation approach based on maximum likelihood linear regression (MLLR) and its feature-space variant, CMLLR. Our preliminary experiments demonstrate that this approach leads to considerable performance improvement, particularly with CMLLR (about 10% relative EER reduction in average). We also...
This paper proposes an adaptive β-order Minimum-Mean-Square-Error (MMSE) estimator for speech enhancement using super-Gaussian speech model (β-SG-MMSE). The spectral amplitude of clean speech is estimated by MMSE estimator under the assumption that the DFT coefficients of clean speech are modeled by super-Gaussian distribution and the DFT coefficients of noise signal are modeled by Gaussian distribution...
This paper presents a novel speech enhancement algorithm based on β-order GARCH (Generalized Auto-regressive Conditional Heteroscedasticity) model. The speech signal is modeled as β-order GARCH process, and the a priori SNR is estimated effectively. The noisy signal is divided into several critical bands, and then the value of order β is updated adaptively according to the signal-to-noise ratios in...
GMM-UBM-based speaker verification heavily relies on a well trained UBM. In practice, it is not often easy to obtain an UBM that fully matches acoustic channels in operation. To solve this problem, we propose a novel sequential MAP adaptation approach: by being sequentially updated with data from new enrollments, the UBM learns and converges to the working channel. Our experiments are conducted on...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.