Audio signal identification via pattern capture and template matching

Kermit, Martin; Eide, Åge

doi:10.1016/s0167-8655(99)00156-7

Cited by 8 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the approach of combing audio track with MIDI sequencer was found out. By using the third-party high-quality audio interface, Studio Vision achieved the simultaneous running of audio track and MIDI track [13][14]. Then Digital Performer, Cakewalk4.0 on the Windows platform and some software products simply used for audio such as Deck and SAW were released.…”

Section: Digital Audio Technologymentioning

confidence: 99%

“…However, because of the complexity of MIDI files, sometimes the main melody cannot be correctly decided considering only the track features. Reference [13] points out that the algorithm of track selection depends to a large extent on the musical styles. If the main melody is observed in tracks, the selection of one main melody track will cause the loss of melody information.…”

Section: P Itc H Tim E mentioning

confidence: 99%

See 1 more Smart Citation

Research on the Computer Music Production Technology System under the Digital Background

Li¹,

Liu²,

Zhang³

et al. 2015

IJMUE

View full text Add to dashboard Cite

show abstract

Section: Digital Audio Technologymentioning

confidence: 99%

Section: P Itc H Tim E mentioning

confidence: 99%

Research on the Computer Music Production Technology System under the Digital Background

Li¹,

Liu²,

Zhang³

et al. 2015

IJMUE

View full text Add to dashboard Cite

show abstract

“…In the first case, the goal would be to classify complete audio sequences, as in the approach by Wang et al [1] who classify TV audio tracks. It is also possible to classify short audio segments (typically less than one second long) in order to detect events in audio sequences, as in the work from Kermit and Eide [2]. Event detection can even be performed in real time [3].…”

Section: Audio Data Analysismentioning

confidence: 99%

A two level strategy for audio segmentation

Lefèvre

Vincent

2011

Digital Signal Processing

View full text Add to dashboard Cite

International audienceIn this paper we are dealing with audio segmentation. The audio tracks are sampled in short sequences which are classified into several classes. Every sequence can then be further analyzed depending on the class it belongs to. We first describe simple techniques for segmentation in two or three classes. These methods rely on amplitude, spectral or cepstral analysis, and classical Hidden Markov Models. From the limitations of these approaches, we propose a two level segmentation process. The segmentation is performed by computing several features for each audio sequence. These features are computed either on a complete audio segment or on a frame (set of samples) which is a subset of the audio segment. The proposed approach for microsegmentation of audio data consists of a combination of a K-mean classifier at the segment level and of a Multidimensional Hidden Markov Model system using the frame decomposition of the signal. A first classification is obtained using the K-mean classifier and segment-based features. Then final result comes from the use of Multidimensional Hidden Markov Models and frame-based features involving temporary results. Multidimensional Hidden Markov Models are an extension of classical Hidden Markov Models dedicated to multicomponent data. They are particularly adapted to our case where each audio segment can be characterized by several features of different natures. We illustrate our methods in the context of analysis of football audio tracks

show abstract

“…In the first case, the goal is to classify complete audio sequences, as in the approach by Wang et al [14] to classify TV audio tracks. It is also possible to classify short audio segments (typically less than one second long) in order to detect events in audio sequences, as in the work from Kermit and Eide [6]. Event detection can even be performed in real time [17].…”

Section: Audio Data Processingmentioning

confidence: 99%