An efficient flicker-free video defogging method is implemented on FPGA and presented in this live demonstration. Considering real-time applications, the proposed design involves a low-cost hardware oriented architecture on an atmospheric scattering model and dark channel prior. The synthesis results show that the design can achieve a processing rate of 200 Mpixels/s by using TSMC 0.13-um technology. Our design is demonstrated on an embedded platform by using Xilinx Spartan-6 FPGA, and the system input could be either static images or videos stream from USB camera.

Sorting is one of the most fundamental topics in computer science. Since partial sorting with lower costs would be much more feasible than the complete sorting method for some applications, this paper focuses on the architecture sorting N values from M inputs. To meet the real-time processing requirement, hardware acceleration is commonly employed to enhance the performance. However, high-speed computation usually raises power consumption drastically.To overcome that problem, a low-power, high-throughput, and modular hardware design of partial sorting network is presented. By applying a pointer-like design, the comparing modules move the indexes of samples instead of moving the input data directly. Power dissipation is reduced by minimizing switching activities and signal transitions. To prevent unnecessary comparing of the large data set, an iterative architecture is proposed which uses both the low-power sorting module and a novel clipping mechanism. The proposed design was simulated with a 90-nm cell library and the results are compared to those of other works on hardware sorting. Experiment results show that power consumption is reduced by 64.9 percent and high-throughput performance can also be achieved.

Monitoring the presence of occupants in a room in a timely manner is a fundamental step for effective building management. Environmental sensor networks have the advantages of high cost-efficiency and non-intrusiveness on privacy and are very suitable for room occupancy detection. Nonlinear discriminative models, e.g., support vector machine and neural networks, have shown good detection performance due to their ability to model complex relationship. However, they tend to produce unstable detection with frequent fluctuations over time, because they regard training data as independent and ignore the prior knowledge of the room occupancy, i.e., not changing very frequently. To improve the stability of the detection, we propose a two-stage structured learning approach with Extreme Learning Machine (ELM) as the local classifier. In the first stage, ELM is used as a fast nonlinear classifier to obtain preliminary detection results. In the second stage, we form data sequences consisting of the current and previous data points. The preliminary detection results by ELM of the data sequences are then used as input to a linear support vector machine for structured output to generate the final detection results. We test the proposed two-stage structured learning approach on a real-world dataset and show that the proposed approach outperforms the related machine learning methods.

Speech summarization, facilitating users to better browse through and understand speech information (especially, spoken documents), has become an active area of intensive research recently. Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem and have shown empirical success for a wide array of summarization tasks. One common deficiency of these approaches is that the corresponding learning criteria are loosely related to the final evaluation metric. To cater for this problem, we present a novel probabilistic framework to learn the summarization models, building on top of the Bayes decision theory. Two effective training criteria, viz. maximum relevance estimation (MRE) and minimum ranking loss estimation (MRLE), deduced from such a framework are introduced to characterize the pair-wise preference relationships between spoken sentences. Experiments on a broadcast news speech summarization task exhibit the performance merits of our summarization methods when compared to existing methods.

Extractive speech summarization attempts to select a representative set of sentences from a spoken document so as to succinctly describe the main theme of the original document. In this paper, we adapt the notion of risk minimization for extractive speech summarization by formulating the selection of summary sentences as a decision-making problem. To this end, we develop several selection strategies and modeling paradigms that can leverage supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. On top of that, various component models are introduced, providing a principled way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. A series of experiments on speech summarization seem to demonstrate that the methods deduced from our summarization framework are very competitive with existing summarization methods.

Query-by-example information retrieval provides users a flexible but efficient way to accurately describe their information needs. The query exemplars are usually long and in the form of either a partial or even a full document. However, they may contain extraneous terms that would have potential negative impacts on the retrieval performance. In order to alleviate those negative impacts, we propose a novel term-based query reduction mechanism so as to improve the informativeness of verbose query exemplars. We also explore the notion of term discrimination power to select a salient subset of query terms automatically. Experiments on the TDT Chinese collection show that the proposed approach is indeed effective and promising.

Imperfect speech recognition often leads to degraded performance when exploiting conventional text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a summarization framework, building on the Kullback-Leibler (KL) divergence measure and exploring both the relevance and topical information cues of spoken documents and sentences, is presented to work with such robust representations. Experiments on broadcast news speech summarization tasks appear to demonstrate the utility of the presented approaches.

Many of the existing machine-learning approaches to speech summarization cast important sentence selection as a two-class classification problem and have shown empirical success for a wide variety of summarization tasks. However, the imbalanced-data problem sometimes results in a trained speech summarizer with unsatisfactory performance. On the other hand, training the summarizer by improving the associated classification accuracy does not always lead to better summarization evaluation performance. In view of such phenomena, we hence investigate two different training criteria to alleviate the negative effects caused by them, as well as to boost the summarizer's performance. One is to learn the classification capability of a summarizer on the basis of the pair-wise ordering information of sentences in a training document according to a degree of importance. The other is to train the summarizer by directly maximizing the associated evaluation score. Experimental results on the broadcast news summarization task show that these two training criteria can give substantial improvements over the baseline SVM summarization system.

Healthcare issues arose from population aging. Meanwhile, electrocardiogram (ECG) is a powerful measurement tool. The first step of ECG is to detect QRS complexes. A state-of-the-art QRS detection algorithm was modified and implemented. By the dedicated architecture design, the novel ASIC is proposed with 2.21 μW power consumption and 0.68mm2core area. It is the smallest QRS detection ASIC so far in the world. In addition, the positive prediction of the ASIC is 99.36% based on the MIT/BIH arrhythmia database certification.

Imperfect speech recognition often leads to degraded performance when leveraging existing text-based methods for speech summarization. To alleviate this problem, this paper investigates various ways to robustly represent the recognition hypotheses of spoken documents beyond the top scoring ones. Moreover, a new summarization method stemming from the Kullback-Leibler (KL) divergence measure and exploring both the sentence and document relevance information is proposed to work with such robust representations. Experiments on broadcast news speech summarization seem to demonstrate the utility of the presented approaches. Index Terms: speech summarization, multiple recognition hypotheses, KL divergence, relevance information

Speech summarization, distilling important information and removing redundant and incorrect information from spoken documents, has become an active area of intensive research in the recent past. In this paper, we consider hybrids of supervised and unsupervised models for extractive speech summarization. Moreover, we investigate the use of the unsupervised summarizer to improve the performance of the supervised summarizer when manual labels are not available for training the latter. A novel training data selection and relabeling approach designed to leverage the inter-document or/and the inter-sentence similarity information is explored as well. Encouraging results were initially demonstrated. Index Terms — Speech summarization, hybrid summarizer, unsupervised training

Heart rate variability (HRV) is a measure of variation in the heart rate. Over the last 25 years, HRV analysis has became utilized more often as a non-invasive research and clinical tool for indirectly investigating both cardiac and autonomic nervous system (ANS) functions in health and disease. In our experiment, 22 healthy subjects and four testing rhythm patterns are studied. How the three musical-rhythmic characteristics of tempo, complexity and drum sample affect the performance of HRV is discussed and a computational model with four factors is proposed. This relationship can help us to improve our life and health by music.

Extractive document summarization automatically selects a number of indicative sentences, passages, or paragraphs from an original document according to a target summarization ratio, and sequences them to form a concise summary. In this article, we present a comparative study of various probabilistic ranking models for spoken document summarization, including supervised classification-based summarizers and unsupervised probabilistic generative summarizers. We also investigate the use of unsupervised summarizers to improve the performance of supervised summarizers when manual labels are not available for training the latter. A novel training data selection approach that leverages the relevance information of spoken sentences to select reliable document-summary pairs derived by the probabilistic generative summarizers is explored for training the classification-based summarizers. Encouraging initial results on Mandarin Chinese broadcast news data are demonstrated.

The performance of current automatic speech recognition (ASR) systems often deteriorates radically when the input speech is corrupted by various kinds of noise sources. Several methods have been proposed to improve ASR robustness over the last few decades. The related literature can be generally classified into two categories according to whether the methods are directly based on the feature domain or consider some specific statistical feature characteristics. In this paper, we present a polynomial regression approach that has the merit of directly characterizing the relationship between speech features and their corresponding distribution characteristics to compensate for noise interference. The proposed approach and a variant were thoroughly investigated and compared with a few existing noise robustness approaches. All experiments were conducted using the Aurora-2 database and task. The results show that our approaches achieve considerable word error rate reductions over the baseline system and are comparable to most of the conventional robustness approaches discussed in this paper.

The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summarization ratio and then sequence them to form a concise summary. In the paper, we present a comparative study of various supervised and unsupervised probabilistic ranking models for spoken document summarization on the Chinese broadcast news. Moreover, we also investigate the possibility of using unsupervised summarizers to boost the performance of supervised summarizers when manual labels are not available for the training of supervised summarizers. Encouraging results were initially demonstrated.

A JPEG XR chip for HD-Photo is implemented with 25 mm2area in TSMC 0.18 um CMOS 1P6M technology at 100 MHz. According to the simulation results, the 4:4:4 1920x1080 HD-Photo 20 frames/sec can be encoded smoothly.

Heart rate variability (HRV) is a measure of variations in the heart rate. Over the last 25 years, HRV analysis has became popular as a non-invasive research and clinical tool for indirectly investigating both cardiac and autonomic nervous system (ANS) function in both health and disease area. How the musical rhythmic characteristics, tempo and complexity, affect the performance of HRV is studied in this work. By understanding the relationship between music and the function of ANS, the novel biomedical entertainment platform is proposed and used for relaxation.

Extractive summarization usually automatically selects indicative sentences from a document according to a certain target summarization ratio, and then sequences them to form a summary. In this paper, we investigate the use of information from relevant documents retrieved from a contemporary text collection for each sentence of a spoken document to be summarized in a probabilistic generative framework for extractive spoken document summarization. In the proposed methods, the probability of a document being generated by a sentence is modeled by a hidden Markov model (HMM), while the retrieved relevant text documents are used to estimate the HMM’s parameters and the sentence’s prior probability. The results of experiments on Chinese broadcast news compiled in Taiwan show that the new methods outperform the previous HMM approach.

The performance of current automatic speech recognition (ASR) systems often deteriorates radically when the input speech is corrupted by various kinds of noise sources. Quite a few of techniques have been proposed to improve ASR robustness over the last few decades. Related work reported in the literature can be generally divided into two aspects according to whether the orientation of the methods is either from the feature domain or from the corresponding probability distributions. In this paper, we present a polynomial regression approach which has the merit of directly characterizing the relationship between the speech features and their corresponding probability distributions to compensate the noise effects. Two variants of the proposed approach are also extensively investigated as well. All experiments are conducted on the Aurora-2 database and task. Experimental results show that for clean-condition training, our approaches achieve considerable word error rate reductions over the baseline system, and also significantly outperform other conventional methods.

This paper considers training data selection for discriminative training of acoustic models for broadcast news speech recognition. Three novel data selection approaches were proposed. First, the average phone accuracy over all hypothesized word sequences in the word lattice of a training utterance was utilized for utterancelevel data selection. Second, phone-level data selection based on the difference between the expected accuracy of a phone arc and the average phone accuracy of the word lattice was investigated. Finally, frame-level data selection based on the normalized frame-level entropy of Gaussian posterior probabilities obtained from the word lattice was explored. The underlying characteristics of the presented approaches were extensively investigated and their performance was verified by comparison with the standard discriminative training approaches. Experiments conducted on the Mandarin broadcast news collected in Taiwan shown that both phone- and frame-level data selection could achieve slight but consistent improvements over the baseline systems at lower training iterations.

With the rapid development of intelligent transportation systems (ITS), how to provide users with a natural and efficient human-machine interface is now becoming a crucial issue for driver safety. It is no doubt that speech will be one of the best mediators of human-machine interaction; however, the performance of automatic speech recognition (ASR) always radically degrades when the input speech is corrupted by varying noises. In this paper, we consider the use of histogram equalization (HEQ) for robust ASR. A novel data fitting scheme was presented to efficiently approximate the inverse of the cumulative density function of training speech for HEQ, which has the merits of lower storage and time consumption compared to the conventional table-lookup or quantile based HEQ approaches. Moreover, a more elaborate attempt of using multiple inverse functions for different noise conditions was investigated as well. All experiments were carried out on the Aurora-2 standard database and task. Very encouraging results were obtained. The proposed robustness technique has also been properly integrated into our prototype system for in-vehicle traffic information retrieval using spoken queries.

This paper considers minimum phone error (MPE) based discriminative training of acoustic models for Mandarin broadcast news recognition. A novel data selection approach based on the normalized frame-level entropy of Gaussian posterior probabilities obtained from the word lattice of the training utterance was explored. It has the merit of making the training algorithm focus much more on the training statistics of those frame samples that center nearly around the decision boundary for better discrimination. Moreover, we presented a new phone accuracy function based on the frame-level accuracy of hypothesized phone arcs instead of using the raw phone accuracy function of MPE training. The underlying characteristics of the presented approaches were extensively investigated and their performance was verified by comparison with the original MPE training approach. Experiments conducted on the broadcast news collected in Taiwan showed that the integration of the frame-level data selection and accuracy calculation could achieve slight but consistent improvements over the baseline system.

Noise robustness is one of the primary challenges facing most automatic speech recognition (ASR) systems. A vast amount of research efforts on preventing the degradation of ASR performance under various noisy environments have been made during the past several years. In this paper, we consider the use of histogram equalization (HEQ) for robust ASR. In contrast to conventional methods, a novel data fitting method based on polynomial regression was presented to efficiently approximate the inverse of the cumulative density functions of speech feature vectors for HEQ. Moreover, a more elaborate attempt of using such polynomial regression models to directly characterizing the relationship between the speech feature vectors and their corresponding probability distributions, under various noise conditions, was proposed as well. All experiments were carried out on the Aurora-2 database and task. The performance of the presented methods were extensively tested and verified by comparison with the other methods. Experimental results shown that for cleancondition training, our method achieved a considerable word error rate reduction over the baseline system, and also significantly outperformed the other methods. Index Terms: noise robustness, speech recognition, histogram equalization, polynomial regression model

The performance of current automatic speech recognition (ASR) systems radically deteriorates when the input speech is corrupted by various kinds of noise sources. Quite a few of techniques have been proposed to improve ASR robustness in the past several years. Histogram equalization (HEQ) is one of the most efficient techniques that have been used to compensate the nonlinear distortion. In this paper, we explored the use of the data fitting scheme to efficiently approximate the inverse of the cumulative density function of training speech for HEQ, in contrast to the conventional tablelookup or quantile based approaches. Moreover, the temporal average operation was also performed on the feature vector components to alleviate the influence of sharp peaks and valleys that were caused by non-stationary noises. Finally, we also investigated the possibility of combining our approaches with other feature discrimination and decorrelation methods. All experiments were carried out on the Aurora-2 database and task. Encouraging results were initially demonstrated. Index Terms: histogram equalization, data fitting, temporal average, robustness