GA-Based Feature Extraction for Clapping Sound Detection

Olajec, J.; Jarina, Roman; Kuba, Michal

doi:10.1109/neurel.2006.341166

Cited by 5 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, different features and techniques are used to detect applauses along with other events like speech, music, cheer and laughter for content-based retrieval. To detect these events in an audio, various time and spectral domain features are used in tandem with machine learning methods [3][4][5][6]. These events play a significant role in golf, baseball and soccer games (or for that matter any sport) for extracting the highlights [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

“…To detect these events in an audio, various time and spectral domain features are used in tandem with machine learning methods [3][4][5][6]. These events play a significant role in golf, baseball and soccer games (or for that matter any sport) for extracting the highlights [3][4][5][6]. Applauses are also used to segment speech meetings for archival and content-based retrieval purposes [7][8][9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Padi

Murthy

2018

Sādhanā

View full text Add to dashboard Cite

Concert recordings of Carnatic music are often continuous and unsegmented. At present, these recordings are manually segmented into items for making CDs. The objective of this paper is to develop algorithms that segment continuous concert recordings into items using applause as a cue. Owing to the 'here and now' nature of applauses, the number of applauses exceeds the number of items in the concert. This results in a concert being fragmented into different segments. In the first part of the paper, applause locations are identified using time, and spectral domain features, namely, short-time energy, zero-crossing rate, spectral flux and spectral entropy. In the second part, inter-applause segments are merged if they belong to the same item. The main component of every item in a concert is a composition. A composition is characterised by an ensemble of vocal (or main instrument), violin (optional) and percussion. Inter-applause segments are classified into three segments, namely, vocal solo, violin solo, composition and thaniavarthanam using tonic normalised cent filterbank cepstral coefficients. Adjacent composition segments are merged into a single item, if they belong to the same melody. Meta-data corresponding to the concert in terms of items, available from listeners, are matched to the segmented audio. The applauses are further classified based on strength using Cumulative Sum. The location of the top three highlights of every concert is documented. The performance of the proposed approaches to applause identification, inter-applause classification and mapping of items is evaluated on 50 live recordings of Carnatic music concerts. The applause identification accuracy is 99%, and the inter-and intra-item classification is 93%, while the mapping accuracy is 95%. Keyword. Cent filter-bank cepstral coefficients; segmentation of concerts; applause detection; classification of music segments. The work presented in this paper is an extension and includes extensive analysis on Carnatic music.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Padi

Murthy

2018

Sādhanā

View full text Add to dashboard Cite

show abstract

“…The previous work optimized only feature subsets (Jarina and Olajec 2007;Olajec et al 2006) or only HMM parameters (Chau et al 1997;Kwong et al 2001Kwong et al , 2002, while other work (Cai et al 2006;Li et al 2008aLi et al , 2008bTemko et al 2008) did not optimize both feature subsets and HMM parameters for discrimination between speech and non-speech events. The features, such as Mel frequency cepstrum coefficients (MFCCs), short time energy (STE), pitch (fundamental frequency, F 0 ), zero crossing rate (ZCR), spectral stability (SS), sub-band energy (SBE), brightness, bandwidth, were used as input to HMMs in the previous work.…”

Section: Introductionmentioning

confidence: 99%

“…The features, such as Mel frequency cepstrum coefficients (MFCCs), short time energy (STE), pitch (fundamental frequency, F 0 ), zero crossing rate (ZCR), spectral stability (SS), sub-band energy (SBE), brightness, bandwidth, were used as input to HMMs in the previous work. Genetic algorithm (GA) was used to optimize only feature subsets in (Jarina and Olajec 2007;Olajec et al 2006) and only HMM parameters in (Chau et al 1997;Kwong et al 2001Kwong et al , 2002. These work showed that better classification results were achieved by optimizing feature subsets or HMM parameters, comparing with the approach without optimization on both feature subsets and HMM parameters.…”

Section: Introductionmentioning

confidence: 99%

Genetic algorithm based simultaneous optimization of feature subsets and hidden Markov model parameters for discrimination between speech and non-speech events

et al. 2010

Int J Speech Technol

View full text Add to dashboard Cite

Feature subsets and hidden Markov model (HMM) parameters are the two major factors that affect the classification accuracy (CA) of the HMM-based classifier. This paper proposes a genetic algorithm based approach for simultaneously optimizing both feature subsets and HMM parameters with the aim to obtain the best HMM-based classifier. Experimental data extracted from three spontaneous speech corpora were used to evaluate the effectiveness of the proposed approach and the three other approaches (i.e. the approaches to single optimization of feature subsets, single optimization of HMM parameters, and no optimization of both feature subsets and HMM parameters) that were adopted in the previous work for discrimination between speech and non-speech events (e.g. filled pause, laughter, applause). The experimental results show that the proposed approach obtains CA of 91.05%, while the three other approaches obtain CA of 86.11%, 87.05%, and 83.16%, respectively. The results suggest that the proposed approach is superior to the previous approaches.

show abstract

“…Recently, more researchers are attracted to the study of detection of unique audio event from sounds [4,6,[15][16][17][18] for different applications, of which gunshot and scream were studied by energy surge and audio feature analysis. Other works [20][21][22] have studied the stress detection from human speech while some researchers worked out some approaches to general sound classification [7,14,23].…”

Section: Introductionmentioning

confidence: 99%

Scream detection for home applications

Huang

Chiew

et al. 2010

2010 5th IEEE Conference on Industrial Electronics and Applications

View full text Add to dashboard Cite

Audio signal is an important clue for the situation awareness. It provides complementary information for video signal. For home care, elder care, and security application, screaming is one of the events people (family member, care giver, and security guard) are especially interested in. We present here an approach to scream detection, using both analytic and statistical features for the classification. In audio features, sound energy is a useful feature to detect scream like audio. We adopt the log energy to detect the energy continuity of the audio to represent the screaming which is often lasting longer than many other sounds. Further, a robust high pitch detection based on the autocorrelation is presented to extract the highest pitch for each frame, followed by a pitch analysis for a time window containing multiple frames. Finally, to validate the scream like sound, a SVM based classifier is applied with the feature vector generated from the MFCCs across a window of frames. Experiments of screaming detection is discussed with promising results shown. The algorithm is ported and run in a Linux based set top box connected by a microphone array to capture the audio for live scream detection.

show abstract

GA-Based Feature Extraction for Clapping Sound Detection

Cited by 5 publications

References 13 publications

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Segmentation of continuous audio recordings of Carnatic music concerts into items for archival

Genetic algorithm based simultaneous optimization of feature subsets and hidden Markov model parameters for discrimination between speech and non-speech events

Scream detection for home applications

Contact Info

Product

Resources

About