DCAR: A Discriminative and Compact Audio Representation for Audio Processing

Jing, Liping; Liu, Bo; Choi, Jaeyoung; Janin, Adam; Bernd, Julia; Mahoney, Michael W.; Friedland, Gerald

doi:10.1109/tmm.2017.2703939

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a different scenario, [57], a highly efficient procedure was proposed for music analysis based on matrix similarity representations to predict the popularity of a certain song according to its similarity with others. In [30], a novel technique for audio representation is presented. In particular, authors proposed DCAR, a two-phased method that outperforms the state-of-art audio representations and has considerable benefits in event detection and audio-scene classification.…”

Section: Background and Related Researchmentioning

confidence: 99%

A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction

et al. 2020

View full text Add to dashboard Cite

The continuous evolution of multimedia applications is fostering applied research in order to dynamically enhance the services provided by platforms such as Spotify, Lastfm, or Billboard. Thus, innovative methods for retrieving specific information from large volumes of data related with music arises as a potential challenge within the Music Information Retrieval (MIR) framework. Moreover, despite the existence of several musical-based datasets, there is still a lack of information to properly assess an accurate estimation of the impact or the popularity of a song within a platform. Furthermore, the aforementioned platforms measure the popularity in various manners, thus increasing the difficulties in performing generalized and comparable models. In this paper, the creation of SpotGenTrack Popularity Dataset (SPD) is presented as an alternative solution to existing datasets that will facilitate researchers when comparing and promoting their models. In addition, an innovative multimodal end-to-end Deep Learning architecture named as HitMusicNet is presented for predicting popularity in music recordings. Experiments conducted show that the proposed architecture outperforms previous studies in the State-of-the-Art by incorporating three main modalities to the analysis, such as audio, lyrics and meta-data as well as a preliminary compression stage via autoencoder to better the capability of the model when predicting the popularity.

show abstract

Section: Background and Related Researchmentioning

confidence: 99%

A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A suitable representation can effectively improve the generalization ability of the model, MFCC and logMel have been proven to be useful in CNNs. [48] presents a novel two-phase method for audio representation, they take into account both global structure and local structure, the learned representation can effectively represent the structure of audio. [49] argue that an image-like spectrogram cannot well capture the complex texture details of the spectrogram, so that they proposed a multichannel LBP feature to improve the robustness to the audio noise.…”

Section: A Audio Classificationmentioning

confidence: 99%

Multi-Representation Knowledge Distillation For Audio Classification

Gao¹,

Xu²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can be transformed into various representations (such as Short Time Fourier Transform and Mel Frequency Cepstral Coefficients), and information implied in different representations can be complementary. Ensembling the models trained on different representations can greatly boost the classification performance, however, making inference using a large number of models is cumbersome and computationally expensive. In this paper, we propose a novel end-to-end collaborative learning framework for the audio classification task. The framework takes multiple representations as the input to train the models in parallel. The complementary information provided by different representations is shared by knowledge distillation. Consequently, the performance of each model can be significantly promoted without increasing the computational overhead in the inference stage. Extensive experimental results demonstrate that the proposed approach can improve the classification performance and achieve state-of-the-art results on both acoustic scene classification tasks and general audio tagging tasks.

show abstract

“…With the arrival of smart video surveillance systems, innovative ways for quickly and effectively detecting malicious occurrences or behaviors in monitored settings based on real-time analysis of multimedia streams have emerged [12], [13]. Most real-world audio recordings are complicated in that they are composed of sequences of many different sounds [9], [14], [15].…”

Section: Introductionmentioning

confidence: 99%

A Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics

et al. 2022

View full text Add to dashboard Cite

With the emergence of new digital technologies, a significant surge has been seen in the volume of multimedia data generated from various smart devices. Several challenges for data analysis have emerged to extract useful information from multimedia data. One such challenge is the early and accurate detection of anomalies in multimedia data. This study proposes an efficient technique for anomaly detection and classification of rare events in audio data. In this paper, we develop a vast audio dataset containing seven different rare events (anomalies) with 15 different background environmental settings (e.g., beach, restaurant, and train) to focus on both detection of anomalous audio and classification of rare sound (e.g., events-baby cry, gunshots, broken glasses, footsteps) events for audio forensics. The proposed approach uses the supreme feature extraction technique by extracting mel-frequency cepstral coefficients (MFCCs) features from the audio signals of the newly created dataset and selects the minimum number of best-performing features for optimum performance using principal component analysis (PCA). These features are input to state-of-theart machine learning algorithms for performance analysis. We also apply machine learning algorithms to the state-of-the-art dataset and realize good results. Experimental results reveal that the proposed approach effectively detects all anomalies and superior performance to existing approaches in all environments and cases.

show abstract

DCAR: A Discriminative and Compact Audio Representation for Audio Processing

Cited by 12 publications

References 34 publications

A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction

A Multimodal End-to-End Deep Learning Architecture for Music Popularity Prediction

Multi-Representation Knowledge Distillation For Audio Classification

A Large-Scale Benchmark Dataset for Anomaly Detection and Rare Event Classification for Audio Forensics

Contact Info

Product

Resources

About