Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

Although research in audio recognition has traditionally focused on speech and music signals, the problem of environmental sound recognition (ESR) has received more attention in recent years. Research on ESR has significantly increased in the past decade. Recent work has focused on the appraisal of non-stationary aspects of environmental sounds, and several new features predicated on non-stationary characteristics have been proposed. These features strive to maximize their information content pertaining to signal's temporal and spectral characteristics. Furthermore, sequential learning methods have been used to capture the long-term variation of environmental sounds. In this survey, we will offer a qualitative and elucidatory survey on recent developments. It includes three parts: i) basic environmental sound processing schemes, ii) stationary ESR techniques and iii) non-stationary ESR techniques. Finally, concluding remarks and future research and development trends in the ESR field will be given.

Environmental sound recognition: A survey

Much work is focused upon music genre recognition (MGR) from audio recordings, symbolic data, and other modalities. While reviews have been written of some of this work before, no survey has been made of the approaches to evaluating approaches to MGR. This paper compiles a bibliography of work in MGR, and analyzes three aspects of evaluation: experimental designs, datasets, and figures of merit.

/pdf/a-survey-of-evaluation-in-music-genre-recognition-29v3l1icya.pdf

A survey of evaluation in music genre recognition

Kernel methods are algorithms that, by replacing the inner product with an appropriate positive definite function, implicitly perform a nonlinear mapping of the input data into a high-dimensional feature space. In this paper, we present a kernel method for clustering inspired by the classical k-means algorithm in which each cluster is iteratively refined using a one-class support vector machine. Our method, which can be easily implemented, compares favorably with respect to popular clustering algorithms, like k-means, neural gas, and self-organizing maps, on a synthetic data set and three UCI real data benchmarks (IRIS data, Wisconsin breast cancer database, Spam database).

A Novel Kernel Method for Clustering.

Although research in audio recognition has traditionally focused on speech and music signals, the problem of environmental sound recognition (ESR) has received more attention in recent years. Research on ESR has significantly increased in the past decade. Recent work has focused on the appraisal of non-stationary aspects of environmental sounds, and several new features predicated on non-stationary characteristics have been proposed. These features strive to maximize their information content pertaining to signal's temporal and spectral characteristics. Furthermore, sequential learning methods have been used to capture the long-term variation of environmental sounds. In this survey, we will offer a qualitative and elucidatory survey on recent developments. It includes four parts: (i) basic environmental sound-processing schemes, (ii) stationary ESR techniques, (iii) non-stationary ESR techniques, and (iv) performance comparison of selected methods. Finally, concluding remarks and future research and development trends in the ESR field will be given.

/pdf/environmental-sound-recognition-a-survey-3av1csbxrm.pdf

Environmental sound recognition: a survey

With the rapid growth in audio data volume, research in the area of content-based audio retrieval has gained impetus in the last decade. Audio classification serves as the fundamental step towards it. Accuracy in classifying data relies on the strength of the features and on the efficacy of classification scheme. In this work, we have focused on the features only. We have restricted ourselves further in the time domain based low level features. Zero crossing rate (ZCR) and shot time energy (STE) are the most widely used features in this category. We have tried to develop the features reflecting the quasi-periodic pattern of the signal by studying the occurrence pattern of ZCR and STE. Co-occurrence matrix for ZCR and STE are formed and features are computed from that to parameterize the signal. For classification, simple k-means clustering is followed and experimental result indicates that proposed features perform better than the traditional feature derived from ZCR and STE.

Speech/Music Classification Using Occurrence Pattern of ZCR and STE

In this work, we have presented a novel simple scheme for classifying audio speech signals into male speech and female speech. In the context of content-based multimedia indexing gender identification based on speech signal is an important task. Some popular salient low level time-domain acoustic features which are very closely related to the physical properties of source audio signal like zero crossing rate (ZCR), short time energy (STE) along with spectral flux, a low level frequency domain feature, are used for this discrimination. RANSAC and Neural-Net has been used as classifier. The experimental result exhibits the efficiency of the proposed scheme.

Automatic male-female voice discrimination

In this work, we have presented a hierarchical scheme for classifying music data Instead of dealing with large variety of features, proposed scheme relies on MFCC and its variants which are introduced at the different stages to satisfy the need At the top level music is classified as song (music with voice) and instrumental (music without voice) based on MFCC Subsequently, instrumental signals and songs are classified based on instrument type and genres respectively Hierarchical approach has been followed for such detailed categorization Using two-stage process, instrumental signals are identified as one of the four types namely, string, woodwind, percussion or keyboard Wavelet and MFCC based features are used for this purpose For song classification, at first level signals are categorized as classical or non-classical(popular) ones by capturing the MFCC pattern present in the high sub-band of wavelet decomposed signal At second level, we consider the task of further classification of popular songs into various genres like Pop, Jazz, Bhangra (an Indian genre) based on amplitude variation pattern RANSAC has been utilized as the classifier at all stages Experimental result indicates the effectiveness of the proposed schemes

Music Classification based on MFCC Variants and Amplitude Variation Pattern: A Hierarchical Approach

Audio classification serves as the fundamental step towards application like content based audio retrieval. In this work, we have tried to exploit the inherent difference in the composition of speech and music signal. A music signal has richer frequency component in comparison to speech signal. Energy distribution of speech and music signal also reflects a pattern that can be used to differentiate the two categories. With these observations, the signal is first decomposed using empirical mode decomposition method. For each decomposed signal, STE and ZCR based features are computed to provide a multiresolution description of the signal. The features thus obtained are used to classify the signals. Experimental result indicates that the performance of the proposed methodology is good enough.

Speech/Music Classification Using Empirical Mode Decomposition

Microblogging, where millions of users exchange messages to share their opinions on different trending and non-trending topics, is one of the popular communication media in recent times. Several researchers are concentrating on these data due to a huge source of information exchanges in online social media. In platforms such as Twitter, dataset-generated lacks coherence, and manually extracting meaning or knowledge from them proves to be painstakingly difficult. It opens up the challenges to the researchers for knowledge extraction driven by a summarization approach. Therefore, automated summary generation tools are recommended to get a meaningful summary out of a given topic becomes crucial in the age of big data. In this work, an unsupervised, extractive summarization model has been proposed. For categorization of data, k-means algorithm has been used, and based on scoring of each document in the corpus, summarization model is designed. The proposed methodology achieves an improved outcome over existing methods, such as lexical rank, sum basic, LSA, etc. evaluated by rouge tool.

Arijit Ghosal

Papers

Speech/Music Classification Using Occurrence Pattern of ZCR and STE

Automatic male-female voice discrimination

Music Classification based on MFCC Variants and Amplitude Variation Pattern: A Hierarchical Approach

Speech/Music Classification Using Empirical Mode Decomposition

Unsupervised Summarization Approach With Computational Statistics of Microblog Data