Content analysis for audio classification and segmentation

By Lie Lu, HongJiang Zhang, Hao Jiang. IEEE Transactions on Speech and Audio Processing, 2002

569 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c5294b2859296116453649e2b6df3717c1390d20

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

A Deep Residual Network for Large-Scale Acoustic Scene Analysis (2019, background): “Audio classification was initially addressed as a single-label task [1, 2, 3, 4, 5, 6].”
Social signal processing: Survey of an emerging domain (2009, methodology): “Typically used techniques include Artificial Neural Networks [5], k Nearest Neighbours [107], Gaussian Mixture Models [61], etc.”
Speaker Diarization: A Review of Recent Research (2010, methodology): “…from each of the speech windows and some criteria are used to determine whether they are best accounted for by two separate models (and hence two separate speakers), or by a single model (and hence the same speaker) by using an empirically determined or dynamically adapted threshold [10], [59].”
Acoustic Scene Classification: Classifying environments from the sounds they produce (2014, methodology): “streams that also rely on the recognition or clustering of sound events have been used for personal archiving [19] and audio segmentation [33] and retrieval [53].”
Scream and gunshot detection and localization for audio-surveillance systems (2007, methodology): “1 Temporal ZCR [7] 2-6 Spectral 4 spectral moments + SFM [8] 7-36 Perceptual 30 MFCC [9] 37-39 Spectral distribution spectral slope, spectral decrease, spectral roll-off [8]”
Toward User-Driven Sound Recognizer Personalization with People Who Are d/Deaf or Hard of Hearing (2021, unknown): “Both studies demonstrated the potential for DHH users to train a sound recognizer; however, several open questions remain; for example, what considerations do DHH users make when recording in environments with real-world acoustic variation—like overlapping sounds and background noise [50]—and what k”
Predicting human interruptibility with sensors (2005, background): “A substantial body of research on segmenting and classifying audio [Lu et al. 2002] can be applied to this problem.”