Distortion-Aware Query-by-Example for Environmental Sounds

Wichern, Gordon; Xue, Jiachen; Thornburg, Harvey; Spanias, Andreas

doi:10.1109/aspaa.2007.4393051

Cited by 5 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1:P ) 1:T are the observed features from the sound query, n is the index of the archived sound n ∈ 1 : N in a database of N sounds, and λ (i) (n) is a HMM estimated from the ith feature trajectory of archived sound n. Details on the estimation of λ (i) (n) and computation of (1) are described in [13].…”

Section: Templates For Content-based Similaritymentioning

confidence: 99%

Unifying semantic and content-based approaches for retrieval of environmental sounds

Wichern

Thornburg

Spanias

2009

2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

Self Cite

View full text Add to dashboard Cite

Creating a database of user-contributed recordings allows sounds to be linked not only by the semantic tags and labels applied to them, but also to other sounds with similar acoustic characteristics. Of paramount importance in navigating these databases are the problems of retrieving similar sounds using text or sound-based queries, and automatically annotating unlabeled sounds. We propose an integrated system, which can be used for text-based retrieval of unlabeled audio, content-based query-by-example, and automatic annotation. To this end, we introduce an ontological framework where sounds are connected to each other based on a measure of perceptual similarity, while words and sounds are connected by optimizing link weights given user preference data. Results on a freely available database of environmental sounds contributed and labeled by non-expert users, demonstrate effective average precision scores for both the text-based retrieval and annotation tasks.

show abstract

Section: Templates For Content-based Similaritymentioning

confidence: 99%

Unifying semantic and content-based approaches for retrieval of environmental sounds

Wichern

Thornburg

Spanias

2009

2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics

Self Cite

View full text Add to dashboard Cite

show abstract

“…To compare sounds, [11] describes a method of estimating L(s i , s j ) = log(P (Y (1:P ) 1:T (s i )|λ (1:P ) (s j ))), the loglikelihood that the feature trajectory of sound s i was generated by the hidden Markov Model (HMM) λ (1:P ) (s j ) built to approximate the simple feature trends of sound s j .…”

Section: Acoustic Information: Sound-to-sound Linksmentioning

confidence: 99%

Combining semantic, social, and acoustic similarity for retrieval of environmental sounds

Mechtley¹,

Wichern²,

Thornburg³

et al. 2010

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

Recent work in audio information retrieval has demonstrated the effectiveness of combining semantic information, such as descriptive, tags with acoustic content. However, these methods largely ignore the possibility of tag queries that do not yet exist in the database and the possibility of similar terms. In this work, we propose a network structure integrating similarity between semantic tags, content-based similarity between environmental audio recordings, and the collective sound descriptions provided by a user community. We then demonstrate the effectiveness of our approach by comparing the use of existing similarity measures for incorporating new vocabulary into an audio annotation and retrieval system.

show abstract

Fast query by example of environmental sounds via robust and efficient cluster-based indexing

Xue

Wichern

Thornburg

et al. 2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Distortion-Aware Query-by-Example for Environmental Sounds

Cited by 5 publications

References 11 publications

Unifying semantic and content-based approaches for retrieval of environmental sounds

Unifying semantic and content-based approaches for retrieval of environmental sounds

Combining semantic, social, and acoustic similarity for retrieval of environmental sounds

Fast query by example of environmental sounds via robust and efficient cluster-based indexing

Contact Info

Product

Resources

About