Filters








1,182 Hits in 4.8 sec

Few-shot acoustic event detection via meta-learning [article]

Bowen Shi, Ming Sun, Krishna C. Puvvada, Chieh-Chi Kao, Spyros Matsoukas, Chao Wang
2020 arXiv   pre-print
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data.  ...  Our analysis including impact of initialization and domain discrepancy further validate the advantage of meta-learning approaches in few-shot AED.  ...  CONCLUSION We formulated and studied few-shot acoustic event detection by comparing typical meta-learning and supervised approaches.  ... 
arXiv:2002.09143v1 fatcat:unbstesf3rhovmxvixvvjwu6ri

Few-Shot Acoustic Event Detection Via Meta Learning

Bowen Shi, Ming Sun, Krishna C. Puvvada, Chieh-Chi Kao, Spyros Matsoukas, Chao Wang
2020 ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data.  ...  We formulate few-shot AED problem and explore different ways of utilizing traditional supervised methods for this setting as well as a variety of meta-learning approaches, which are conventionally used  ...  CONCLUSION We formulated and studied few-shot acoustic event detection by comparing typical meta-learning and supervised approaches.  ... 
doi:10.1109/icassp40776.2020.9053336 dblp:conf/icassp/ShiSPKMW20 fatcat:rxe47zpue5evhd5ayk4cwbm22a

Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers [article]

Piper Wolters, Chris Daw, Brian Hutchinson, Lauren Phillips
2021 arXiv   pre-print
These represent absolute improvements of 0.200 and 0.234 over strong proposal-free few-shot sound event detection baselines.  ...  In this paper, we propose novel approaches to few-shot sound event detection utilizing region proposals and the Perceiver architecture, which is capable of accurately localizing sound events with very  ...  , by modifying the model-agnostic meta-learning algorithm [23] .  ... 
arXiv:2107.13616v1 fatcat:qvp553hrerfm7clpi7ggrbjxlu

Gerçek Ortamlarda Artımlı Öğrenme ile Gerçek Zamanlı İşitsel Sahne Analizi

Barış BAYRAM, Gökhan İNCE
2020 European Journal of Science and Technology  
The learning process is investigated by conducting a variety of experiments to evaluate the performance of Unknown Event Detection (UED), Acoustic Event Recognition (AER), and continual learning using  ...  The continual learning is employed via a time-series algorithm, Hidden Markov Model (HMM), on these feature sets from acoustic signals stemming from the sources.  ...  In [42] , few-shot method based on meta-learning has been presented for acoustic event detection to detect the unknown acoustic classes.  ... 
doi:10.31590/ejosat.779710 fatcat:5i2rwdh23ndgzkr7dy4redk7my

Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection [article]

Chendong Zhao, Jianzong Wang, Leilai Li, Xiaoyang Qu, Jing Xiao
2022 arXiv   pre-print
Sound event detection is to infer the event by understanding the surrounding environmental sounds.  ...  Meanwhile, few-shot learning methods promise a good generalization ability when facing a new limited-data task. Recent approaches have achieved promising results in this field.  ...  Few-shot sound event detection Recent approaches [13] , [17] , [19] adopt the prototypical networks [23] and graph neural networks [26] for few-shot sound event detection.  ... 
arXiv:2205.11738v1 fatcat:paby7e5fqzgzxdgz6itnd3yv3i

Meta-SE: A meta-learning framework for few-shot speech enhancement

Weili Zhou, Mingliang Lu, Ruijie Ji
2021 IEEE Access  
CONCLUSION This work proposes to solve the few-shot speech enhancement problem via meta-learning.  ...  PRELIMINARY FOR META-LEARNING Meta-learning has become the research focus of few-shot learning due to its capability of quickly process new tasks with few samples by the prior meta-knowledge.  ... 
doi:10.1109/access.2021.3066609 fatcat:kjdirvjkwbgmbayngkx7dreq5q

Generalizing from a Few Examples: A Survey on Few-Shot Learning [article]

Yaqing Wang and Quanming Yao and James Kwok and Lionel M. Ni
2020 arXiv   pre-print
Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-Shot Learning (FSL) is proposed to tackle this problem.  ...  Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems.  ...  By continuously refining θ 0 using the few-shot samples in D train , the meta-learner improves its θ 0 to quickly adapt to the few-shot training set.  ... 
arXiv:1904.05046v3 fatcat:t3ipecry4vc2thzdu6sv65epwa

A Real-time Robot-based Auxiliary System for Risk Evaluation of COVID-19 Infection [article]

Wenqi Wei, Jianzong Wang, Jiteng Ma, Ning Cheng, Jing Xiao
2020 arXiv   pre-print
It is based on real conversation data from human-robot, which processes speech signals to detect cough and classifies it if detected.  ...  It combines real-time speech recognition, temperature measurement, keyword detection, cough detection and other functions in order to convert live audio into actionable structured data to achieve the COVID  ...  To achieve this, we introduce the c-way k-shot few shot learning algorithm proposed by Vinyals et al [21] .  ... 
arXiv:2008.07695v1 fatcat:fh2zko5kefap3dgiiwudyqafc4

Who calls the shots? Rethinking Few-Shot Learning for Audio [article]

Yu Wang, Nicholas J. Bryan, Justin Salamon, Mark Cartwright, Juan Pablo Bello
2021 arXiv   pre-print
Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set.  ...  This leads to unanswered questions concerning the impact such audio properties may have on few-shot learning system design, performance, and human-computer interaction, as it is typically up to the user  ...  Lastly, recent few-shot image classification work has shown that a simple logistic regression or LR model trained on top of a pre-trained embedding outperforms many meta-learning based algorithms [15]  ... 
arXiv:2110.09600v1 fatcat:rj3475lmsvgv7p6hmvyazdo45e

A Real-Time Robot-Based Auxiliary System for Risk Evaluation of COVID-19 Infection

Wenqi Wei, Jianzong Wang, Jiteng Ma, Ning Cheng, Jing Xiao
2020 Interspeech 2020  
It is based on real conversation data from human-robot, which processes speech signals to detect cough and classifies it if detected.  ...  It combines real-time speech recognition, temperature measurement, keyword detection, cough detection and other functions in order to convert live audio into actionable structured data to achieve the COVID  ...  To achieve this, we introduce the c-way k-shot few shot learning algorithm proposed by Vinyals et al [21] .  ... 
doi:10.21437/interspeech.2020-2105 dblp:conf/interspeech/WeiWMCX20 fatcat:24vkac4qpfag5io2fh5xyu5wxa

Surrogate regression modelling for fast seismogram generation and detection of microseismic events in heterogeneous velocity models

Saptarshi Das, Xi Chen, Michael P Hobson, Suhas Phadke, Bertwim van Beest, Jeroen Goudswaard, Detlef Hohl
2018 Geophysical Journal International  
In this paper, starting from Graphics Processing Unit (GPU) based synthetic simulations of a few thousand forward seismic shots due to microseismic events via pseudo-spectral solution of elastic wave equation  ...  in a Bayesian analysis for microseismic event detection.  ...  Fast Computation of the Likelihood Function Using the Trained Surrogate Meta-Models Formulation of the Likelihood Function for Detecting Microseismic Events In this section, we use the best surrogate  ... 
doi:10.1093/gji/ggy283 fatcat:shjrbiinrjdqtkkohdyddr54a4

A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification

Varun Kumar, Hadrien Glaude, Cyprien de Lichy, Wlliam Campbell
2019 Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)  
We formulate it as a Few-Shot Integration (FSI) problem where a few examples are used to introduce a new intent.  ...  In this paper, we study six feature space data augmentation methods to improve classification performance in FSI setting in combination with both supervised and unsupervised representation learning methods  ...  In , authors propose to learn a weighted combination of metrics obtained from meta-training tasks for a newly seen few-shot task.  ... 
doi:10.18653/v1/d19-6101 dblp:conf/acl-deeplo/KumarGLC19 fatcat:2h5y4hzu3rcpzhc2mppsvgfgam

Event Mining in Multimedia Streams

Lexing Xie, H. Sundaram, M. Campbell
2008 Proceedings of the IEEE  
We discuss five main aspects of an event detection system.  ...  The review includes detection of events and actions in one or more continuous sequences, events in edited video streams, unsupervised event discovery, events in a collection of media objects, and a discussion  ...  Kernel-based classifiers have been used to detect events from within a shot broadcast content. Shots in TV broadcasts tend to be only a few seconds long.  ... 
doi:10.1109/jproc.2008.916362 fatcat:b3utldtbwvehjo4brlnteetdbq

ChMusic: A Traditional Chinese Music Dataset for Evaluation of Instrument Recognition [article]

Xia Gong, Yuxiang Zhu, Haidi Zhu, Haoran Wei
2021 arXiv   pre-print
“A Reweighted Meta Learning Framework for Robust Few Shot Learning,” arXiv preprint arXiv:2011.06782, 2020. [34] H. Wei, F. Tao, R. Su, S. Yang, J. Liu.  ...  “Fair meta-learning for few-shot classification,” In 2020 IEEE International Conference on Knowledge Graph (ICKG), 2020, pp. 275-282. [39] H. Wei and N.  ... 
arXiv:2108.08470v2 fatcat:j27fecw2b5cihmvrnpjridjpcu

Table of Contents

2021 IEEE Transactions on Signal Processing  
Dai (Contents Continued on Page ix) Learning to Demodulate From Few Pilots via Offline and Online Meta-Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Lai Blind Direction-of-Arrival Estimation in Acoustic Vector-Sensor Arrays via Tensor Decomposition and Kullback-Leibler Cheng Adaptive Radar Detection and Classification Algorithms for Multiple Coherent  ... 
doi:10.1109/tsp.2021.3136798 fatcat:kzkdhzcz3fgx3jv6gfjofooseq
« Previous Showing results 1 — 15 out of 1,182 results