Blind Change Detection for Audio Segmentation

Omar, Mohamed Kamal; Chaudhari, Upendra V.; Ramaswamy, Ganesh N.

doi:10.1109/icassp.2005.1415160

Cited by 15 publications

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In model-based approaches, Gaussian mixture models (GMM) [4], [5], Hidden Markov Models (HMM) [6], Bayesian [7], and Artificial Neural Networks (ANN) [8] have all been applied to the task of segmentation. Examples of an unsupervised audio segmentation approach can be found in [7] and [9]. These unsupervised approaches test the likelihood ratio between two hypotheses of change and no change for a given observation sequence.…”

Section: Related Workmentioning

confidence: 99%

A two phase method for general audio segmentation

Zhang

Whalley

Brooks

2009

2009 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

This paper presents a model-free and training-free twophase method for audio segmentation that separates monophonic heterogeneous audio files into acoustically homogeneous regions where each region contains a single sound. A rough segmentation separates audio input into audio clips based on silence detection in the time domain. Then a self-similarity matrix, based on selected audio features in the frequency domain to discover the level of similarity between frames in the audio clip, is calculated. Subsequently an edge detection method is used to find regions in the similarity image that determine plausible sounds in the audio clip. The results of the two phases are combined to form the final boundaries for the input audio. This two-phase method is evaluated using established methods and a standard non-musical database. The method reported here offers more accurate segmentation results than existing methods for audio segmentation. We propose that this approach could be adapted as an efficient preprocessing stage in other audio processing systems such as audio retrieval, classification, music analysis and summarization.

show abstract

Section: Related Workmentioning

confidence: 99%

A two phase method for general audio segmentation

Zhang

Whalley

Brooks

2009

2009 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

“…More general audio segmentation frameworks employ kernel methods to compute the distance-based segmentation in a high-dimensional feature space [5], [6], and informationtheoretic methods based on entropy [7], or on test statistics such as the CUSUM algorithm [8], [9]. As discussed later, the traditional CUSUM approaches undergo approximations for parameter estimation, resulting in practical shortcomings when change points may occur rapidly such as in audio signals.…”

Section: A Backgroundmentioning

confidence: 99%

An Information-Geometric Approach to Real-Time Audio Segmentation

Dessein

Cont

2013

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

To cite this version:Arnaud Dessein, Arshia Cont. An information-geometric approach to real-time audio segmentation. IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2013, 20 (4) Abstract-We present a generic approach to real-time audio segmentation in the framework of information geometry for exponential families. The proposed system detects changes by monitoring the information rate of the signals as they arrive in time. We also address shortcomings of traditional cumulative sum approaches to change detection, which assume known parameters before change. This is done by considering exact generalized likelihood ratio test statistics, with a complete estimation of the unknown parameters in the respective hypotheses. We derive an efficient sequential scheme to compute these statistics through convex duality. We finally provide results for speech segmentation in speakers, and polyphonic music segmentation in note slices.

show abstract

“…. , yn ≥ N ( 1, Δ1) Here parameters 0 = { 0, Δ0} are estimated from a few samples in the beginning of the observation sequence, and 1 = { 1, Δ1} from the end of the observation sequence [4]. Thus the models are only estimated once for a given observation sequence and are independent of the change point.…”

Section: Cumulative Summentioning

confidence: 99%

“…CUSUM is another segmentation algorithm used in a variety of change detection problems [4]. Under the assumption that each yi is drawn from an independent, identically distributed process, the CUSUM test has been shown to be optimal in minimizing the detection time for a given false alarm rate [7].…”

Section: Cumulative Summentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Audio Segmentation using Extended Baum-Welch Transformations

Sainath¹,

Kanevsky

Iyengar

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

View full text Add to dashboard Cite

Audio segmentation has applications in a variety of contexts, such as audio information retrieval, automatic sound analysis, and as a pre-processing step in speech recognition. Extended Baum-Welch (EBW) transformations are most commonly used as a discriminative technique for estimating parameters of Gaussian mixtures. In this paper, we derive an unsupervised audio segmentation approach using these transformations. We nd that our algorithm outperforms both the Bayesian Information Criterion (BIC) and Cumulative Sum (CUSUM) segmentation methods. In particular, our EBW segmentation algorithm provides improvements over the baseline approaches in detecting landmarks of short duration and minimizing landmark oversegmentation. In addition, we show that the EBW approach provides faster computation compared to the baseline methods.

show abstract

Blind Change Detection for Audio Segmentation

Cited by 15 publications

References 4 publications

A two phase method for general audio segmentation

A two phase method for general audio segmentation

An Information-Geometric Approach to Real-Time Audio Segmentation

Unsupervised Audio Segmentation using Extended Baum-Welch Transformations

Contact Info

Product

Resources

About