Environmental sound classification with convolutional neural networks

By Karol J. Piczak. 2015

919 citations recorded by the source corpus.

Subfields: Developmental Biology, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Developmental Biology

In Signal Processing

Citations in the corpus

FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, background): “[17], convolutional neural networks (CNN) [18], recurrent neural networks (RNN) [19], or combinations thereof [20].”
Moments in Time Dataset: One Million Videos for Event Understanding (2018, background): “[41] collected an early dataset and assembled a challenge for sound classification, Piczak [32] collected a dataset of fifty sound categories and enough to train deep convolutional models, Salamon et al.”
Between-Class Learning for Image Classification (2017, background): “Deep convolutional neural networks (CNNs) [18] have achieved high performance in various tasks, such as image recognition [17, 11], speech recognition [1, 21], and sound recognition [19, 26].”
Parameter Efficient Multimodal Transformers for Video Representation Learning (2020, methodology): “…2019), DPC (Han et al., 2019), CBT (Sun et al., 2019a), MultiSens (Owens & Efros, 2018), AVTS (Korbar et al., 2018), AE (Aytar et al., 2016), SVM (Piczak, 2015a), RF (Piczak, 2015a),ConvNet(Piczak,2015b),SoundNet(Aytaretal.,2016), L 3…”
SoundNet: Learning Sound Representations from Unlabeled Video (2016, background): “Even though there are unsupervised [20] and supervised [27, 23, 6, 12] deep learning methods applied to sound classification, the models are limited by the amount of available labeled natural sound data.”
Audioclip: Extending Clip to Image, Text and Audio (2021, methodology): “To successfully solve this task, different approaches were proposed that included the use of one- [27,28] or two-dimensional Convolutional Neural Networks (CNN) operating on static [18,24,32,9,15,17,33,8,30] or trainable [23,10] time-frequency transformation of raw audio.”
Look, Listen, and Learn More: Design Choices for Deep Audio Embeddings (2019, background): “Machine listening is an active area of research concerned with the development of computational methods to derive meaning from sound, in which the use of deep learning has seen growing popularity and success [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13].”
CNN-Based Learnable Gammatone Filterbank and Equal-Loudness Normalization for Environmental Sound Classification (2020, methodology): “As in many other fields such as computer vision and natural language processing, convolutional neural networks (CNNs) [12] have shown outstanding performance for ESC [13]–[21].”
Very deep convolutional neural networks for raw waveforms (2016, methodology): “8% accuracy, competitive with CNNs using log-mel spectrogram inputs [11].”
A Deep Residual Network for Large-Scale Acoustic Scene Analysis (2019, methodology): “In this work, we focus on deep convolutional neural networks (CNNs) for audio classification due to the success in many prior studies [14, 15, 16, 17, 18, 19].”
A Closer Look at Weak Label Learning for Audio Events (2018, methodology): “More recently several deep learning methods, especially using Convolutional Neural Networks [31], [32], [33], [34] have been proposed for audio event classiﬁcation and detection.”
Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification (2016, methodology): “To the left of the dashed line we present the performance of the proposed model on the original datast without augmentation.”
Wavelet Networks: Scale Equivariant Learning From Raw Waveforms (2020, methodology): “MAXPOOL: 5X1 FLATTEN 196× 6→ 1152 FC: [1152, 96] FC: [96, 48] FC: [48, 10] SOFTMAX Table 3: Proposed wavelet network variant of the 50999-1DCNN of Abdoli et al.”
Training general-purpose audio tagging networks with noisy labels and iterative self-verification (2018, background): “Naturally, a large number of similar architectures and neural networks have proven to be powerful tools in this setting [6, 7, 8, 9, 10, 11].”
Self-Supervised Learning by Cross-Modal Audio-Video Clustering (2019, neutral): “3 Piczak ConvNet [48] 64.”
Look, Listen and Learn (2017, neutral): “3% Piczak ConvNet [26] 64.”
Filterbank learning for deep neural network based polyphonic sound event detection (2016, background): “Recently, deep neural networks (DNN), which are neural networks with multiple hidden layers, have been shown to give better results in sound event detection [6], [20], [21], [22], [23].”
SpeechMix - Augmenting Deep Sound Recognition Using Hidden Space Interpolations (2020, methodology): “Piczak [20] proposed to apply CNNs to the”