SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks (2020-03-03T00:00:00.000000Z)

TL;DR

The proposed framework (SELD-TCN) outperforms the state-of-the-art SELDnet performance on four different datasets and achieves 4x faster training time per epoch and 40x faster inference time on an ordinary graphics processing unit (GPU).

Abstract

The understanding of the surrounding environment plays a critical role in autonomous robotic systems, such as self-driving cars. Extensive research has been carried out concerning visual perception. Yet, to obtain a more complete perception of the environment, autonomous systems of the future should also take acoustic information into account. Recent sound event localization and detection (SELD) frameworks utilize convolutional recurrent neural networks (CRNNs). However, considering the recurrent nature of CRNNs, it becomes challenging to implement them efficiently on embedded hardware. Not only are their computations strenuous to parallelize, but they also require high memory bandwidth and large memory buffers. In this work, we develop a more robust and hardware-friendly novel architecture based on a temporal convolutional network (TCN). The proposed framework (SELD-TCN) outperforms the state-of-the-art SELDnet performance on four different datasets. Moreover, SELD-TCN achieves 4x faster training time per epoch and 40x faster inference time on an ordinary graphics processing unit (GPU).

Authors

Bin Yang

2 papers

Sherif Abdulatif

2 papers

Karim Guirguis

1 papers

TL;DR

Abstract

Authors

References42 items

Polyphonic Sound Event Detection Using Convolutional Bidirectional Lstm and Synthetic Data-based Transfer Learning

Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network

End-to-end Convolutional Neural Networks for Sound Event Detection in Urban Environments

Unifying Isolated and Overlapping Audio Event Detection with Multi-label Multi-task Convolutional Recurrent Neural Networks

End-to-End Polyphonic Sound Event Detection Using Convolutional Recurrent Neural Networks with Learned Time-Frequency Representation Input

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

Deep Neural Network Based Multichannel Audio Source Separation

Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features

Duration-Controlled LSTM for Polyphonic Sound Event Detection

Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network

Virtual Adversarial Training and Data Augmentation for Acoustic Event Detection with Gated Recurrent Neural Networks

A Wavenet for Speech Denoising

Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features

Hardware accelerators for recurrent neural networks on FPGA

Broadband doa estimation using convolutional neural networks trained with noise signals

Efficient Processing of Deep Neural Networks: A Tutorial and Survey

Sound event detection using spatial features and convolutional recurrent neural network

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Discriminative multiple sound source localization based on deep neural networks using independent location model

WaveNet: A Generative Model for Raw Audio

A neural network based algorithm for speaker localization in a multi-room environment

Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks

Recent advances in convolutional neural networks

Recurrent Neural Networks Hardware Implementation on FPGA

An Efficient Temporally-Constrained Probabilistic Model for Multiple-Instrument Music Transcription

A learning-based approach to direction of arrival estimation in noisy and reverberant environments

Robust sound event recognition using convolutional neural networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

The Diverse Environments Multi-channel Acoustic Noise Database (DEMAND): A database of multichannel environmental noise recordings

Context-dependent sound event detection

Estimating animal population density using passive acoustics

NMF-based environmental sound source separation using time-variant gain features

Automatic Audio Indexing and Audio Playback Speed Control as Tools for Language Learning

TUT Sound Events 2018 - Ambisonic, Reverberant and Real-life Impulse Response Dataset

Adversarial

Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries

On sound source localization of speech signals using deep neural networks

Challenge on Detection and Classification of Acoustic Scenes and Events ACOUSTIC EVENT DETECTION USING SIGNAL ENHANCEMENT AND SPECTRO-TEMPORAL FEATURE EXTRACTION

Real-Time Detection of Overlapping Sound Events with Non-Negative Matrix Factorization

Sound Event Detection in Multisource Environments Using Source Separation

Musical Instrument Recognition in Polyphonic Audio Using Source-Filter Model for Sound Separation

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names