On classification of environmental acoustic data using crowds

@article{Zhang2017OnCO,
  title={On classification of environmental acoustic data using crowds},
  author={Shan Zhang and Aditya Vempaty and Susan E. Parks and Pramod K. Varshney},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={5880-5884}
}
In this work, we use crowds for acoustic classification of animal species in supervised and unsupervised manners. We demonstrate the effectiveness of the proposed triplet based crowdsourcing systems via actual experiments. Moreover, we propose a generalized 1-bit RPCA algorithm to further improve classification performance. The unique marriage of crowdsourcing and generalized 1-bit RPCA algorithm is shown to yield excellent performance for acoustic data classification. 

Figures and Tables from this paper

Machine learning from crowds: A systematic review of its applications

This work has analyzed many applications of machine learning using crowdsourced data following a systematic methodology, classifying them into different fields of study, highlighting several of their characteristics and showing the recent interest in the use of crowdsourcing for machine learning.

MechanicalHeart: A Human-Machine Framework for the Classification of Phonocardiograms

A framework for combining machine learning algorithms, crowd workers, and experts in the classification of heart sound recordings achieves greater performance than a baseline classifier alone, utilizing less expert resources while achieving similar performance, compared to a framework without the crowd.

Copula-based Multimodal Data Fusion for Inference with Dependent Observations

This dissertation investigates inference problems with heterogeneous modalities by taking into account nonlinear cross-modal dependence, and proposes a novel parallel platform, C-Storm, by marrying copula-based dependence modeling for highly accurate inference and a highly-regarded parallel computing platform Storm for fast stream data processing.

References

SHOWING 1-10 OF 21 REFERENCES

Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach.

This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with M IML classifiers.

Classification of large acoustic datasets using machine learning and crowdsourcing: application to whale calls.

Sounds recorded by audio sensors carried by killer whales and pilot whales close to the coasts of Norway, Iceland, and the Bahamas were analyzed using computer methods and citizen scientists as part of the Whale FM project to show that at least some whales from these two locations have different acoustic repertoires that can be sensed by the computer analysis.

Reliable Crowdsourcing for Multi-Class Labeling Using Coding Theory

An ordering principle for the quality of crowds is developed and it is shown that pairing among workers and diversification of the questions help in improving system performance, and use of good codes may improve the performance of the crowdsourcing task over typical majority-voting approaches.

Adaptively Learning the Crowd Kernel

An algorithm that, given n objects, learns a similarity matrix over all n2 pairs, from crowdsourced data alone is introduced, and SVMs reveal that the crowd kernel captures prominent and subtle features across a number of domains.

Crowdclustering with Sparse Pairwise Labels: A Matrix Completion Approach

It is shown, both theoretically and empirically, that the proposed approach for crowclustering needs only a small number of manual annotations to obtain an accurate data partition, highlighting the trade-off between a large number of noisy crowdsourced labels and aSmall number of high quality labels.

Automatic identification of bird species based on sinusoidal modeling of syllables

Test how well bird species can be recognized by comparing simple sinusoidal representations of isolated syllables shows that, with limited sets of bird species, a recognizer based on this signal model may already be sufficient.

Stochastic triplet embedding

A new technique called t-Distributed Stochastic Triplet Embedding (t-STE) is introduced that collapses similar points and repels dissimilar points in the embedding - even when all triplet constraints are satisfied.

Wavelets in Recognition of Bird Sounds

This paper presents a novel method to recognize inharmonic and transient bird sounds efficiently using wavelet decomposition and recognition using either supervised or unsupervised classifier.

Methods for automatic detection of mysticete sounds

Methods for the automatic recognition of low‐frequency sounds of baleen whales are presented and spectrogram correlation is implemented and found effective at detection of blue whale vocalizations in the presence of interfering sounds.

Matrix recovery from quantized and corrupted measurements

Experimental results on synthetic and two real-world collaborative filtering datasets demonstrate that directly operating with the quantized measurements - rather than treating them as real values - results in (often significantly) lower recovery error if the number of quantization bins is less than about 10.