Corpus ID: 27988446

Applause identification and its relevance to archival of Carnatic music

  title={Applause identification and its relevance to archival of Carnatic music},
  author={Sarala Padi and Vignesh Ishwar and Ashwin Bellur and H. Murthy},
Comunicacio presentada al 2nd CompMusic Workshop, celebrat els dies 12 i 13 de juliol de 2012 a Istanbul (Turquia), organitzat per CompMusic. 

Figures and Tables from this paper

Cent Filter-Banks and its Relevance to Identifying the Main Song in Carnatic Music
Song identification is performed on 50 live recordings of Carnatic music and a new feature called Cent Filter-bank based Cepstral Coefficients (CFCC) that is tonic invariant is proposed, showing that CFCC features give promising results for CarnaticMusic processing tasks. Expand
Segmentation of continuous audio recordings of Carnatic music concerts into items for archival
The objective of this paper is to develop algorithms that segment continuous concert recordings into items using applause as a cue, and the proposed approaches to applause identification, inter-applause classification and mapping of items are evaluated. Expand
Video temporal segmentation using applause sound and end-of-act detection for a circus performance video archive
Typically, archival performance videos are: filmed in a single shot, lengthy, affected by camera operation, and originate from various video formats. To be useful, a video of a whole performanceExpand
Novel audio features for capturing tempo salience in music recordings
By a quantitative analysis within an Indian music scenario, it is demonstrated that the novel audio features introduced in this paper capture the aspect of tempo salience well, while being independent of continuous fluctuations and local changes in tempo. Expand
Inter and Intra Item Segmentation of Continuous Audio Recordings of Carnatic Music for Archival
To segment carnatic music recordings into individual items for archival purposes using applauses, raga information is used to merge adjacent segments belonging to the same item. Expand
Modeling and Analysis of Indian Carnatic Music Using Category Theory
The power and flexibility of conceptual modeling techniques based on a branch of mathematics called category theory (CT), using the structure of Carnatic music as an example, are demonstrated and a platform for collaboration and research sharing in this area is described. Expand
An approach for Mridanga stroke transcription in Carnatic music using HGCC
A new feature extraction method called Harmonic Grouping Cepstral Coefficient(HGCC) is introduced, which follows steps similar to MFCC during extraction the deviation lies in filters used for extraction. Expand
Unsupervised Segmentation of Songs in Full Concert Audio
Tens of millions of full live concerts are available on videoand audiosharing services, and set lists with song time annotations are an essential information provided with them. Since the manualExpand
Identification of live or studio versions of a song via supervised learning
It is proposed to classify automatically a music data set by using Machine Learning techniques under a supervised setting and is proven to perform with high accuracy on a 1066-song data set with distinct genres and across different languages. Expand


Discriminative Feature Selection for Applause Sounds Detection
  • R. Jarina, J. Olajec
  • Computer Science
  • Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '07)
  • 2007
The results show that the applause sound recognition improves if only a few coefficients are selected from MFCC static and dynamic features. Expand
Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework
We developed a unified framework to extract highlights from three sports: baseball, golf and soccer by detecting some of the common audio events that are directly indicative of highlights. We usedExpand
Novel approach for detecting applause in continuous meeting speech
A robust and automated applause detection algorithm for meeting speech using mel frequency cepstral coefficients (MFCC) feature vectors and Gaussian mixture model (GMM) as classifier is proposed. Expand
Improving Markov Model Based Music Piece Structure Labelling with Acoustic Information
The acoustic model proposed in this paper is based on the assumption that the parts with the same label even in different pieces share some acoustic properties compared to other parts in the same pieces and improves the labelling accuracy over the baseline method. Expand
A robust audio classification and segmentation method
A robust algorithm that is capable of segmenting and classifying an audio stream into speech, music, environment sound and silence is presented and some new features such as the noise frame ratio and band periodicity are introduced. Expand
Automatic singer identification
  • Tong Zhang
  • Computer Science
  • 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)
  • 2003
A system for automatic singer identification is developed which recognizes the singer of a song by analyzing the music signal by following the framework of common speaker identification systems. Expand
A comparison of features for speech, music discrimination
This paper examines the discrimination achieved by several different features using common training and test sets and the same classifier on four types of feature, amplitude, cepstra, pitch and zero-crossings. Expand
The DET curve in assessment of detection task performance
The DET Curve is introduced as a means of representing performance on detection tasks that involve a tradeoff of error types and why it is likely to produce approximately linear curves. Expand
Theory and Applications of Digital Speech Processing
This new text presents the basic concepts and theories of speech processing with clarity and currency, while providing hands-on computer-based laboratory experiences for students. Expand
Real-Time Detection of Stealthy DDoS Attacks Using Time-Series Decomposition
  • Haiqin Liu, M. Kim
  • Computer Science
  • 2010 IEEE International Conference on Communications
  • 2010
A detection approach based on time-series decomposition, which divides the original time series into trend and random components and applies a double autocorrelation technique and an improved cumulative sum technique to the trend andrandom components to detect anomalies in both components is proposed. Expand