• Corpus ID: 7859040

Shortest Path Techniques for Annotation and Retrieval of Environmental Sounds

@inproceedings{Mechtley2012ShortestPT,
  title={Shortest Path Techniques for Annotation and Retrieval of Environmental Sounds},
  author={Brandon Mechtley and Andreas Spanias and Perry R. Cook},
  booktitle={ISMIR},
  year={2012}
}
Many techniques for text-based retrieval and automatic annotation of music and sound effects rely on learning with explicit generalization, training individual classifiers for each tag. Non-parametric approaches, where queries are individually compared to training instances, can provide added flexibility, both in terms of robustness to shifts in database content and support for foreign queries, such as concepts not yet included in the database. In this paper, we build upon prior work in… 

Figures from this paper

Techniques for soundscape retrieval and synthesis
TLDR
This dissertation examines the application of several computational tools in the realms of digital signal processing, multimedia information retrieval, and computer music synthesis to the analysis of the soundscape.
Freesound technical demo
TLDR
This demo wants to introduce Freesound to the multimedia community and show its potential as a research resource.

References

SHOWING 1-10 OF 22 REFERENCES
Unifying semantic and content-based approaches for retrieval of environmental sounds
TLDR
An ontological framework is introduced where sounds are connected to each other based on a measure of perceptual similarity, while words andSounds are connected by optimizing link weights given user preference data, which demonstrates effective average precision scores for both the text-based retrieval and annotation tasks.
An Ontological Framework for Retrieving Environmental Sounds Using Semantics and Acoustic Content
TLDR
This work introduces an ontological framework where sounds are connected to each other based on the similarity between acoustic features specifically adapted to environmental sounds, while semantic tags andSounds are connected through link weights that are optimized based on user-provided tags.
Semantic Annotation and Retrieval of Music and Sound Effects
We present a computer audition system that can both annotate novel audio tracks with semantically meaningful words and retrieve relevant tracks from a database of unlabeled audio content given a
Automatic sound annotation
  • P. Cano, M. Koppenberger
  • Computer Science
    Proceedings of the 2004 14th IEEE Signal Processing Society Workshop Machine Learning for Signal Processing, 2004.
  • 2004
TLDR
A nearest-neighbor classifier with a database of isolated sounds unambiguously linked to WordNet concepts, a semantic network that organizes real world knowledge, is used to overcome the need of a huge number of classifiers to distinguish many different sound classes.
Segmentation, Indexing, and Retrieval for Environmental and Natural Sounds
TLDR
A dynamic Bayesian network (DBN) is presented that jointly infers onsets and end times of the most prominent sound events in the space, along with an extension of the algorithm for covering large spaces with distributed microphone arrays.
Combining semantic, social, and acoustic similarity for retrieval of environmental sounds
TLDR
This work proposes 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 and demonstrates the effectiveness of this approach by comparing the use of existing similarity measures for incorporating new vocabulary into an audio annotation and retrieval system.
Annotating Music Collections: How Content-Based Similarity Helps to Propagate Labels
TLDR
The main goal of the work is to ease the process of annotating huge music collections, by using content-based similarity distances as a way to propagate labels among songs.
Combining Feature Kernels for Semantic Music Retrieval
TLDR
This work uses 4 different types of acoustic content and social context feature sets to describe a large music corpus and derive 4 individual kernel matrices from these feature sets, which are used to train a support vector machine (SVM) classifier for each semantic tag in a large tag vocabulary.
Acoustic topic model for audio information retrieval
TLDR
The proposed acoustic topic model shows promising results by outperforming the Latent Perceptual Indexing method in classifying onomatopoeia descriptions and semantic descriptions in audio description classification tasks using Support Vector Machine on the BBC database.
Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy
TLDR
This work uses WordNet, a semantic network that organizes real world knowledge, to tackle the taxonomy definition problem and uses a nearest-neighbor classifier with a database of isolated sounds unambiguously linked to WordNet concepts to overcome the need of a huge number of classifiers.
...
1
2
3
...