Few-Shot Acoustic Event Detection Via Meta Learning

Shi, Bowen; Sun, Ming; Puvvada, Krishna C.; Kao, Chieh-Chi; Matsoukas, Spyros; Wang, Chao

doi:10.1109/icassp40776.2020.9053336

Cited by 48 publications

(33 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, Meta-learning is widely active in image classification [16,[28][29], image recognition [17,30], object detection [18,[31][32], and text classification [19] and other computer vision and natural language processing fields. And it has gradually drawn much attention in speech recognition [20], audio event recognition [21,33], text-to-speech [22], speaker recognition [23] and other areas of speech signal processing. In these scenarios, samples of the new categories may be inherently scarce, or their annotation tags may be difficult to obtain.…”

Section: A Related Work In Meta-learningmentioning

confidence: 99%

Meta-SE: A Meta-Learning Framework for Few-Shot Speech Enhancement

Zhou

2021

IEEE Access

View full text Add to dashboard Cite

Separating target speech from noisy signal is important for many realistic applications. Recently, deep neural network (DNN) has been widely used in speech enhancement (SE) and obtained prominent performance improvements. However, the current deep models require a large amount of training data to obtain a good performance. It is still challenging to construct an effective deep speech enhancement model with actual few training samples. At present, 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, but there are very few works applying meta-learning on few-shot speech enhancement. In this paper, we propose a generic meta-learning framework Meta-SE which applies the U-Net as the metalearner, to tackle the few-shot speech enhancement problem. Meta-SE is trained and optimized with the changed speech enhancement tasks to obtain meta-knowledge, and towards better capability of fast and good generalizing to the new unseen noises with few training samples. The experiment results show that the proposed method not only outperforms the state-of-the-arts DNN-SE models under the few-shot conditions, but also learns a more general and flexible model for task adaption. INDEX TERMS Speech enhancement, single-channel, meta-learning, few-shot learning This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.

show abstract

Section: A Related Work In Meta-learningmentioning

confidence: 99%

Meta-SE: A Meta-Learning Framework for Few-Shot Speech Enhancement

Zhou

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…C is the total number of target events. Supervised few-shot acoustic event classification [2] aims to train a model using a large set of labeled base class data C train . The goal is to detect novel class data C test with only few labeled samples for each novel event available.…”

Section: Overviewmentioning

confidence: 99%

“…Further, building personalized audio event detectors for smart home assistants such as Alexa, Google Home or Siri requires building models with extremely limited data (e.g., < 10 samples). Few-shot AEC via meta-learning has been proposed as a solution for building models in low data regimes [2].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised and Semi-Supervised Few-Shot Acoustic Event Classification

Huang

Puvvada

Sun

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Few-shot Acoustic Event Classification (AEC) aims to learn a model to recognize novel acoustic events using very limited labeled data. Previous works utilize supervised pre-training as well as meta-learning approaches, which heavily rely on labeled data. Here, we study unsupervised and semisupervised learning approaches for few-shot AEC. Our work builds upon recent advances in unsupervised representation learning introduced for speech recognition and language modeling. We learn audio representations from a large amount of unlabeled data, and use the resulting representations for few-shot AEC. We further extend our model in a semi-supervised fashion. Our unsupervised representation learning approach outperforms supervised pre-training methods, and our semi-supervised learning approach outperforms meta-learning methods for few-shot AEC. We also show that our work is more robust under domain mismatch.

show abstract

“…In addition, for few-shot learning and novelty detection, some studies have utilized acoustic data to generalize an audio class with few number of examples, and detect novel audio classes. In [42], few-shot method based on meta-learning has been presented for acoustic event detection to detect the unknown acoustic classes. Also, only a few works exist using unsupervised algorithms for novelty detection.…”

Section: Related Workmentioning

confidence: 99%

Gerçek Ortamlarda Artımlı Öğrenme ile Gerçek Zamanlı İşitsel Sahne Analizi

Bayram¹,

İnce²

2020

European Journal of Science and Technology

View full text Add to dashboard Cite

Continual learning for scene analysis is a continuous process to incrementally learn distinct events, actions, and even noise models from past experiences using different sensory modalities. In this paper, an Auditory Scene Analysis (ASA) approach based on a continual learning system is developed to incrementally learn the acoustic events in a dynamically-changing domestic environment. The events being salient sound sources are localized by a Sound Source Localization (SSL) method to robustly process the signals of the localized sound source in the domestic scene where multiple sources can co-exist. For real-time ASA, audio patterns are segmented from the acoustic signal stream of the localized source for extraction of the audio features, and construction of a feature set for each pattern. 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. 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 a Hierarchical HMM algorithm. The Hierarchical HMM consists of two layers: 1) a lower layer in which AER is performed using an HMM for each event and the event-wise likelihood thresholds; and 2) an upper layer in which UED is achieved by one HMM with a suspicion threshold through the audio features with their proto symbols stemming from the lower layer HMMs. We verified the effectiveness of the proposed system capable of continual learning, AER and UED in terms of False-Positive Rates, True-Positive Rates, recognition accuracy and computational time to meet the demands in a learning task of multiple events in real-time. The effectiveness of the AER system has been verified with high accuracy, and a short retraining time in real-time ASA having nine different sounds.

show abstract

Few-Shot Acoustic Event Detection Via Meta Learning

Cited by 48 publications

References 11 publications

Meta-SE: A Meta-Learning Framework for Few-Shot Speech Enhancement

Meta-SE: A Meta-Learning Framework for Few-Shot Speech Enhancement

Unsupervised and Semi-Supervised Few-Shot Acoustic Event Classification

Gerçek Ortamlarda Artımlı Öğrenme ile Gerçek Zamanlı İşitsel Sahne Analizi

Contact Info

Product

Resources

About