Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes

Kumar, Anurag; Khadkevich, Maksim; Fügen, Christian

doi:10.1109/icassp.2018.8462200

Cited by 113 publications

(99 citation statements)

References 19 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This shows the importance of high-level data augmentation for extracting more discriminating features. Table 5 compares the performance of the proposed classification approach to the state-of-the-art pre-trained classifiers (AlexNet and GoogLeNet) on environmental sound datasets following the transfer learning and fine-tuning strategies explained in [75]. It is worth mentioning that, these two pre-trained networks have been fine-tuned on the 2D aggregation (pooling) of STFT, MFCC, and CRP.…”

Section: Aimentioning

confidence: 99%

Unsupervised feature learning for environmental sound classification using Weighted Cycle-Consistent Generative Adversarial Network

Esmaeilpour

Cardinal

Koerich

2020

Applied Soft Computing

View full text Add to dashboard Cite

In this paper we propose a novel environmental sound classification approach incorporating unsupervised feature learning via the spherical K-Means++ algorithm and a new architecture for high-level data augmentation. The audio signal is transformed into a 2D representation using a discrete wavelet transform (DWT). The DWT spectrograms are then augmented by a novel architecture for cycle-consistent generative adversarial network. This high-level augmentation bootstraps generated spectrograms in both intra-and inter-class manners by translating structural features from sample to sample. A codebook is built by coding the DWT spectrograms with the speeded-up robust feature detector and the K-Means++ algorithm. The Random forest is the final learning algorithm which learns the environmental sound classification task from the code vectors. Experimental results in four benchmarking environmental sound datasets (ESC-10, ESC-50, UrbanSound8k, and DCASE-2017) have shown that the proposed classification approach outperforms most of the state-of-the-art classifiers, including convolutional neural networks such as AlexNet and GoogLeNet, improving the classification rate between 3.51% and 14.34%, depending on the dataset.

show abstract

Section: Aimentioning

confidence: 99%

Unsupervised feature learning for environmental sound classification using Weighted Cycle-Consistent Generative Adversarial Network

Esmaeilpour

Cardinal

Koerich

2020

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…Network design: The backbone network is based on the simple yet powerful CNN structure, which has been widely used in audio tasks [16,17]. The input feature of network is a mel-spectrograms, with 128 frequency bins and 160 frames.…”

Section: Experimental Settingsmentioning

confidence: 99%

Learning to Match Transient Sound Events Using Attentional Similarity for Few-shot Sound Recognition

Chou

Cheng

Jang

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we introduce a novel attentional similarity module for the problem of few-shot sound recognition. Given a few examples of an unseen sound event, a classifier must be quickly adapted to recognize the new sound event without much fine-tuning. The proposed attentional similarity module can be plugged into any metric-based learning method for few-shot learning, allowing the resulting model to especially match related short sound events. Extensive experiments on two datasets show that the proposed module consistently improves the performance of five different metricbased learning methods for few-shot sound recognition. The relative improvement ranges from +4.1% to +7.7% for 5-shot 5-way accuracy for the ESC-50 dataset, and from +2.1% to +6.5% for noiseESC-50. Qualitative results demonstrate that our method contributes in particular to the recognition of transient sound events.

show abstract

“…Meanwhile, tagging the sound events consumes amounts of manpower. To address this problem, two kinds of approaches have been proposed: one efficiently making use of limited data [15][16][17][18][19] and the other based on additional data [3,20,21]. In the Figure 1: Architecture of the end-to-end audio classification network.…”

Section: Related Workmentioning

confidence: 99%

“…However, these augmentation methods are not suitable for a multi-label dataset, such as Audio Set. In the second type, Kumar et al [21] pre-trained the model by an additional large audio dataset. Kong et al [3] applied the rich sound representation learned on YouTube-100M [4] to classify Audio Set.…”

Section: Related Workmentioning

confidence: 99%

An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy

Chen¹,

Jing²,

Chen³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even overlapping. This paper introduces an end-to-end audio classification system based on raw waveforms and mix-training strategy. Compared to human-designed features which have been widely used in existing research, raw waveforms contain more complete information and are more appropriate for multi-label classification. Taking raw waveforms as input, our network consists of two variants of ResNet structure which can learn a discriminative representation. To explore the information in intermediate layers, a multi-level prediction with attention structure is applied in our model. Furthermore, we design a mix-training strategy to break the performance limitation caused by the amount of training data. Experiments show that the mean average precision of the proposed audio classification system on Audio Set dataset is 37.2%. Without using extra training data, our system exceeds the state-of-the-art multi-level attention model.

show abstract

Knowledge Transfer from Weakly Labeled Audio Using Convolutional Neural Network for Sound Events and Scenes

Cited by 113 publications

References 19 publications

Unsupervised feature learning for environmental sound classification using Weighted Cycle-Consistent Generative Adversarial Network

Unsupervised feature learning for environmental sound classification using Weighted Cycle-Consistent Generative Adversarial Network

Learning to Match Transient Sound Events Using Attentional Similarity for Few-shot Sound Recognition

An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy

Contact Info

Product

Resources

About