A GMM/HMM model for reconstruction of missing speech spectral components for continuous speech recognition

This paper presents a method for reconstructing unreliable spectral components of speech signals using the statistical distributions of the clean components. Our goal is to model the temporal patterns in speech signal and take advantage of correlations between speech features in both time and frequency domain simultaneously. In this approach, a hidden Markov model (HMM) is first trained on clean speech data to model the temporal patterns which appear in the sequences of the spectral components. Using this model and according to the probabilities of occurring noisy spectral component at each states, a probability distributions for noisy components are estimated. Then, by applying maximum a posteriori (MAP) estimation on the mentioned distributions, the final estimations of the unreliable spectral components are obtained. The proposed method is compared to a common missing feature method which is based on the probabilistic clustering of the feature vectors and also to a state of the art method based on sparse reconstruction. The experimental results exhibits significant improvement in recognition accuracy over a noise polluted Persian corpus.     

Emotional speech feature normalization and recognition based on speaker-sensitive feature clustering

In this paper we propose a feature normalization method for speaker-independent speech emotion recognition. The performance of a speech emotion classifier largely depends on the training data, and a large number of unknown speakers may cause a great challenge. To address this problem, first, we extract and analyse 481 basic acoustic features. Second, we use principal component analysis and linear discriminant analysis jointly to construct the speaker-sensitive feature space. Third, we classify the emotional utterances into pseudo-speaker groups in the speaker-sensitive feature space by using fuzzy k-means clustering. Finally, we normalize the original basic acoustic features of each utterance based on its group information. To verify our normalization algorithm, we adopt a Gaussian mixture model based classifier for recognition test. The experimental results show that our normalization algorithm is effective on our locally collected database, as well as on the eNTERFACE’05 Audio-Visual Emotion Database. The emotional features achieved using our method are robust to the speaker change, and an improved recognition rate is observed.     

Study of sub-word acoustical models for <Emphasis Type="Italic">Kannada</Emphasis> isolated word recognition system

The speech recognition system basically extracts the textual information present in the speech. In the present work, speaker independent isolated word recognition system for one of the south Indian language—Kannada has been developed. For European languages such as English, large amount of research has been carried out in the context of speech recognition. But, speech recognition in Indian languages such as Kannada reported significantly less amount of work and there are no standard speech corpus readily available. In the present study, speech database has been developed by recording the speech utterances of regional Kannada news corpus of different speakers. The speech recognition system has been implemented using the Hidden Markov Tool Kit. Two separate pronunciation dictionaries namely phone based and syllable based dictionaries are built in-order to design and evaluate the performances of phone-level and syllable-level sub-word acoustical models. Experiments have been carried out and results are analyzed by varying the number of Gaussian mixtures in each state of monophone Hidden Markov Model (HMM). Also, context dependent triphone HMM models have been built for the same Kannada speech corpus and the recognition accuracies are comparatively analyzed. Mel frequency cepstral coefficients along with their first and second derivative coefficients are used as feature vectors and are computed in acoustic front-end processing. The overall word recognition accuracy of 60.2 and 74.35 % respectively for monophone and triphone models have been obtained. The study shows a good improvement in the accuracy of isolated-word Kannada speech recognition system using triphone HMM models compared to that of monophone HMM models.     

Simulation and overall comparative evaluation of performance between different techniques for high band feature extraction based on artificial bandwidth extension of speech over proposed global system for mobile full rate narrow band coder

This paper addresses a novel approach to investigate, study and simulate computation of high band (HB) feature extraction based on linear predictive coding (LPC) and mel frequency cepstral coefficient (MFCC) techniques. Further, HB features are embedded into encoded bitstream of proposed global system for mobile (GSM) full rate (FR) 06.10 coder using joint source coding and data hiding before being transmitted to receiving terminal. At receiver, HB features are extracted to reproduce HB portion of speech and for the same different extension of excitation techniques are applied and their results evaluated in terms of quality (intelligibility and naturalness) and bandwidth. MATLAB based e-test bench is created for implementing the proposed artificial bandwidth extension (ABE) coder following series of simulations, that are carried out to discover and gain insight about the performance of it using subjective [mean opinion score (MOS)] and objective [perceptual evaluation of speech quality (PESQ)] analysis. The results obtained for both the analyses advocate that proposed ABE coder outperforms proposed GSM FR NB (legacy GSM FR) coder. While the fact remains that, compared to LPC based parameterizations over ABE coder, MFCC parameterization results in higher speech intelligibility which is evident from obtained slightly better PESQ and MOS scores.     

Advanced methods for the estimation of an unknown projection from a map

This article presents three new methods (M5, M6, M7) for the estimation of an unknown map projection and its parameters. Such an analysis is beneficial and interesting for historic, old, or current maps without information about the map projection; it could improve their georeference. The location similarity approach takes into account the residuals on the corresponding features; the minimum is found using the non-linear least squares. For the shape similarity approach, the minimized objective function ? takes into account the spatial distribution of the features, together with the shapes of the meridians, parallels and other 0D-2D elements. Due to the non-convexity and discontinuity, its global minimum is determined using the global optimization, represented by the differential evolution. The constant values of projection φ _k , λ _k , φ ₁, λ ₀, and map constants R,ΔX,ΔY, α (in relation to which the methods are invariant) are estimated. All methods are compared and the results are presented for the synthetic data as well as for 8 early maps from the Map Collection of the Charles University and the David Rumsay Map Collection. The proposed algorithms have been implemented in the new version of the detectproj software.     

Location K-anonymity in indoor spaces

With the expansion of wireless-communication infrastructure and the evolution of indoor positioning technologies, the demand for location-based services (LBS) has been increasing in indoor as well as outdoor spaces. However, we should consider a significant challenge regarding the location privacy for realizing indoor LBS. To avoid violations of location privacy, much research has been performed, and location \(\mathcal {K}\)-anonymity has been intensively studied to blur a user location with a cloaking region involving at least \(\mathcal {K}-1\) locations of other persons. Owing to the differences between indoor and outdoor spaces, it is, however, difficult to apply this approach directly in an indoor space. First, the definition of the distance metric in indoor space is different from that in Euclidean and road-network spaces. Second, a bounding region, which is a general form of an anonymizing spatial region (ASR) in Euclidean space, does not respect the locality property in indoor space, where movement is constrained by building components. Therefore, we introduce the concept of indoor location \(\mathcal {K}\)-anonymity in this paper. Then, we investigate the requirements of ASR in indoor spaces and propose novel methods to determine the ASR, considering hierarchical structures of the indoor space. While indoor ASRs are determined at the anonymizer, we also propose processing methods for r-range queries and k-nearest-neighbor queries at a location-based service provider. We validate our methods with experimental analysis of query-processing performance and resilience against attacks in indoor spaces.     

Exploring cell tower data dumps for supervised learning-based point-of-interest prediction (industrial paper)

Exploring massive mobile data for location-based services becomes one of the key challenges in mobile data mining. In this paper, we investigate a problem of finding a correlation between the collective behavior of mobile users and the distribution of points of interest (POIs) in a city. Specifically, we use large-scale cell tower data dumps collected from cell towers and POIs extracted from a popular social network service, Weibo. Our objective is to make use of the data from these two different types of sources to build a model for predicting the POI densities of different regions in the covered area. An application domain that may benefit from our research is a business recommendation application, where a prediction result can be used as a recommendation for opening a new store/branch. The crux of our contribution is the method of representing the collective behavior of mobile users as a histogram of connection counts over a period of time in each region. This representation ultimately enables us to apply a supervised learning algorithm to our problem in order to train a POI prediction model using the POI data set as the ground truth. We studied 12 state-of-the-art classification and regression algorithms; experimental results demonstrate the feasibility and effectiveness of the proposed method.     

Studying high impact fix-inducing changes

As software systems continue to play an important role in our daily lives, their quality is of paramount importance. Therefore, a plethora of prior research has focused on predicting components of software that are defect-prone. One aspect of this research focuses on predicting software changes that are fix-inducing. Although the prior research on fix-inducing changes has many advantages in terms of highly accurate results, it has one main drawback: It gives the same level of impact to all fix-inducing changes. We argue that treating all fix-inducing changes the same is not ideal, since a small typo in a change is easier to address by a developer than a thread synchronization issue. Therefore, in this paper, we study high impact fix-inducing changes (HIFCs). Since the impact of a change can be measured in different ways, we first propose a measure of impact of the fix-inducing changes, which takes into account the implementation work that needs to be done by developers in later (fixing) changes. Our measure of impact for a fix-inducing change uses the amount of churn, the number of files and the number of subsystems modified by developers during an associated fix of the fix-inducing change. We perform our study using six large open source projects to build specialized models that identify HIFCs, determine the best indicators of HIFCs and examine the benefits of prioritizing HIFCs. Using change factors, we are able to predict 56 % to 77 % of HIFCs with an average false alarm (misclassification) rate of 16 %. We find that the lines of code added, the number of developers who worked on a change, and the number of prior modifications on the files modified during a change are the best indicators of HIFCs. Lastly, we observe that a specialized model for HIFCs can provide inspection effort savings of 4 % over the state-of-the-art models. We believe our results would help practitioners prioritize their efforts towards the most impactful fix-inducing changes and save inspection effort.     

An empirical study of integration activities in distributions of open source software

Reuse of software components, either closed or open source, is considered to be one of the most important best practices in software engineering, since it reduces development cost and improves software quality. However, since reused components are (by definition) generic, they need to be customized and integrated into a specific system before they can be useful. Since this integration is system-specific, the integration effort is non-negligible and increases maintenance costs, especially if more than one component needs to be integrated. This paper performs an empirical study of multi-component integration in the context of three successful open source distributions (Debian, Ubuntu and FreeBSD). Such distributions integrate thousands of open source components with an operating system kernel to deliver a coherent software product to millions of users worldwide. We empirically identified seven major integration activities performed by the maintainers of these distributions, documented how these activities are being performed by the maintainers, then evaluated and refined the identified activities with input from six maintainers of the three studied distributions. The documented activities provide a common vocabulary for component integration in open source distributions and outline a roadmap for future research on software integration.