An Audio-Based Sports Video Segmentation and Event Detection Algorithm

Abstract

Abstract

Data-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast News

“…The performance of each method for the full feature vector (i.e. C1, 2,3,4,5), showed in Table 2, is repeated here for the convenience of comparison.…”

“…The availability of these resources has led research to focus on a vast number of applications related to automatic processing of such multimedia data including TV program automatic handling, story classification, automatic highlighting of events, sports news handling, automatic transcription extraction, automatic commercial detection, summarization etc. [1][2][3][4][5][6][7][8][9] Concerning the audio data, the automatic analysis of the audio signals can offer the users useful information. In the case of broadcast news, automatic processing is related to tasks such as sound recognition, 10,11 speaker recognition, 12 anchor detection, 13 role detection, [14][15][16] story boundary detection, 2,17,18 summary construction from anchor talking, 9,19 channel's quality detection, 20 sound event detection, 21,22 non-linguistic humanproduced sounds detection, 5,6,[23][24][25] audio type segmentation in sport games, 4,26,27 highlight scene extraction from sports games, 3 violence scene detection, 28 music characteristics classification, 29,30 jingle detection, 1 commercial block detection, 8 voice activity detection, 31 language recognition, 32 emotion recognition 33 and speech recognition.…”

Automatic Audio Classification and Speaker Identification for Video Content Analysis

“…based classification and segmentation [5,10,12,13,15,16], HMM-based event detection algorithm [9], selfsimilarity analysis (spectral clustering) based segmentation and summarization [16][17][18], GMM-based speaker or signer recognition [24][25][26][27]. They all have their own advantages and shortcomings, such as low accuracy of rule-based method, high computing complexity of SVM-based audio classification and spectral clustering based segmentation.…”

“…Audio, as another timedependent media in video documents, can supplement visual information and supply a unique cue for video content analysis and retrieval [3]. Recently, more audio-assisted techniques for video content analysis are proposed [1][2][3][4][5][6][7][8][9][10][11], most of them are pertinent to specific domain like news video [2,3,6], sports video [7][8][9], instructional video [10] and colonoscopy video [11].…”

Parallel model combination and word recognition in soccer audio

“…Audio therefore has a crucial role to play in automatic highlighting and to perform the task audio cue schemes have typically been used to bridge the gap between different levels of information. It is a general approach used consistently among [2] and [3], to bridge low level (audio features) to high level (game events) and helps parse semantic content. Along with such crowd and other audio cues the commentator can also provide extra information, with the emotional content giving a sense of mood and words linking directly to events.…”