http://hdl.handle.net/10016/2315 Tue, 18 Jun 2013 06:17:02 GMT 2013-06-18T06:17:02Z http://hdl.handle.net/10016/15932 Title: Auditory-inspired morphological processing of speech spectrograms: applications in automatic speech recognition and speech enhancement Author(s): Cadore, Joyner; Valverde-Albacete, Francisco J.; Gallardo-Antolín, Ascensión; Peláez-Moreno, Carmen Abstract: New auditory-inspired speech processing methods are presented in this paper, combining spectral subtraction and two-dimensional non-linear filtering techniques originally conceived for image processing purposes. In particular, mathematical morphology operations, like erosion and dilation, are applied to noisy speech spectrograms using specifically designed structuring elements inspired in the masking properties of the human auditory system. This is effectively complemented with a pre-processing stage including the conventional spectral subtraction procedure and auditory filterbanks. These methods were tested in both speech enhancement and automatic speech recognition tasks. For the first, time-frequency anisotropic structuring elements over grey-scale spectrograms were found to provide a better perceptual quality than isotropic ones, revealing themselves as more appropriate—under a number of perceptual quality estimation measures and several signal-to-noise ratios on the Aurora database—for retaining the structure of speech while removing background noise. For the second, the combination of Spectral Subtraction and auditory-inspired Morphological Filtering was found to improve recognition rates in a noise-contaminated version of the Isolet database. Wed, 31 Oct 2012 23:00:00 GMT http://hdl.handle.net/10016/15932 2012-10-31T23:00:00Z http://hdl.handle.net/10016/15680 Title: Real-time robust automatic speech recognition using compact support vector machines Author(s): Solera-Ureña, R.; García-Moral, Ana I.; Peláez-Moreno, Carmen; Martínez-Ramón, Manel; Díaz-de-María, Fernando Abstract: In the last years, support vector machines (SVMs) have shown excellent performance in many applications, especially in the presence of noise. In particular, SVMs offer several advantages over artificial neural networks (ANNs) that have attracted the attention of the speech processing community. Nevertheless, their high computational requirements prevent them from being used in practice in automatic speech recognition (ASR), where ANNs have proven to be successful. The high complexity of SVMs in this context arises from the use of huge speech training databases with millions of samples and highly overlapped classes. This paper suggests the use of a weighted least squares (WLS) training procedure that facilitates the possibility of imposing a compact semiparametric model on the SVM, which results in a dramatic complexity reduction. Such a complexity reduction with respect to conventional SVMs, which is between two and three orders of magnitude, allows the proposed hybrid WLS-SVC/HMM system to perform real-time speech decoding on a connected-digit recognition task (SpeechDat Spanish database). The experimental evaluation of the proposed system shows encouraging performance levels in clean and noisy conditions, although further improvements are required to reach the maturity level of current context-dependent HMM based recognizers. Mon, 30 Apr 2012 22:00:00 GMT http://hdl.handle.net/10016/15680 2012-04-30T22:00:00Z http://hdl.handle.net/10016/14353 Title: In-layer multi-buffer framework for rate-controlled scalable video coding Author(s): Sanz-Rodríguez, Sergio; Díaz-de-María, Fernando Abstract: Temporal scalability is supported in scalable video coding (SVC) by means of hierarchical prediction structures, where the higher layers can be ignored for frame rate reduction. Nevertheless, this kind of scalability is not totally exploited by the rate control (RC) algorithms since the hypothetical reference decoder (HRD) requirement is only satisfied for the highest frame rate sub-stream of every dependency (spatial or coarse grain scalability) layer. In this paper we propose a novel RC approach that aims to deliver several HRD-compliant temporal resolutions within a particular dependency layer. Instead of using the common SVC encoder configuration consisting of a dependency layer per each temporal resolution, a compact configuration that does not require additional dependency layers for providing different HRD-compliant temporal resolutions is proposed. Specifically, the proposed framework for rate-controlled SVC uses a set of virtual buffers within a dependency layer so that their levels can be simultaneously controlled for overflow and underflow prevention while minimizing the reconstructed video distortion of the corresponding sub-streams. This in-layer multi-buffer approach has been built on top of a baseline H.264/SVC RC algorithm for variable bit rate applications. The experimental results show that our proposal achieves a good performance in terms of mean quality, quality consistency, and buffer control using a reduced number of layers. Sat, 31 Dec 2011 23:00:00 GMT http://hdl.handle.net/10016/14353 2011-12-31T23:00:00Z http://hdl.handle.net/10016/13118 Title: Two Information-Theoretic Tools to Assess the Performance of Multi-class Classifiers Author(s): Valverde-Albacete, Francisco J.; Peláez-Moreno, Carmen Abstract: We develop two tools to analyze the behavior of multiple-class, or multi-class, classifiers by means of entropic measures on their confusion matrix or contingency table. First we obtain a balance equation on the entropies that captures interesting properties of the classifier. Second, by normalizing this balance equation we first obtain a 2-simplex in a three-dimensional entropy space and then the de Finetti entropy diagram or entropy triangle. We also give examples of the assessment of classifiers with these tools. Tue, 31 Aug 2010 22:00:00 GMT http://hdl.handle.net/10016/13118 2010-08-31T22:00:00Z