Positive and negative sampling strategies for self-supervised learning on audio-video data

In Self-Supervised Learning (SSL), Audio-Visual Correspondence (AVC) is a popular task to learn deep audio and video features from large unlabeled datasets. The key step in AVC is to randomly sample audio and video clips from the dataset and learn to minimize the feature distance between the positive pairs (corresponding audio-video pair) while maximizing the distance between the negative pairs (non-corresponding audio-video pairs). The learnt features are shown to be effective on various downstream tasks. However, these methods achieve subpar performance when the size of the dataset is rather small. In this paper, we investigate the effect of utilizing class label information in the AVC feature learning task. We modified various positive and negative data sampling techniques of SSL based on class label information to investigate the effect on the feature quality. We propose a new sampling approach which we call soft-positive sampling, where the positive pair for one audio sample is not from the exact corresponding video, but from a video of the same class. Experimental results suggest that when the dataset size is small in SSL setup, features learnt through the soft-positive sampling method significantly outperform those from the traditional SSL sampling approaches. This trend holds in both in-domain and out-of-domain downstream tasks, and even outperforms supervised classification. Finally, experiments show that class label information can easily be obtained using a publicly available classifier network and then can be used to boost the SSL performance without adding extra data annotation burden.

Zero-Shot Audio Classification using Image Embeddings

Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and time-consuming. Zero-shot learning models are capable of classifying the unseen concepts by utilizing their semantic information. The present study introduces image embeddings as side information on zero-shot audio classification by using a nonlinear acoustic-semantic projection. We extract the semantic image representations from the Open Images dataset and evaluate the performance of the models on an audio subset of AudioSet using semantic information in different domains; image, audio, and textual. We demonstrate that the image embeddings can be used as semantic information to perform zero-shot audio classification. The experimental results show that the image and textual embeddings display similar performance both individually and together. We additionally calculate the semantic acoustic embeddings from the test samples to provide an upper limit to the performance. The results show that the classification performance is highly sensitive to the semantic relation between test and training classes and textual and image embeddings can reach up to the semantic acoustic embeddings when the seen and unseen classes are semantically similar.

Low-complexity acoustic scene classification in DCASE 2022 Challenge

This paper analyzes the outcome of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task is a continuation from the previous years. In this edition, the requirement for low-complexity solutions were modified including: a limit of 128 K on the number of parameters, including the zero-valued ones, imposed INT8 numerical format, and a limit of 30 million multiply-accumulate operations at inference time. The provided baseline system is a convolutional neural network which employs post-training quantization of parameters, resulting in 46512 parameters, and 29.23 million multiply-and-accumulate operations, well under the set limits of 128K and 30 million, respectively. The baseline system has a 42.9% accuracy and a log-loss of 1.575 on the development data consisting of audio from 9 different devices. An analysis of the submitted systems will be provided after the challenge deadline.

Sound Event Detection: A Tutorial

The goal of automatic sound event detection (SED) methods is to recognize what is happening in an audio signal and when it is happening. In practice, the goal is to recognize at what temporal instances different sounds are active within an audio signal. This paper gives a tutorial presentation of sound event detection, including its definition, signal processing and machine learning approaches, evaluation, and future perspectives.

Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems

This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task consisted of classification of data from multiple devices, requiring good generalization properties, using low-complexity solutions. The provided baseline system is based on a CNN architecture and post-training parameters quantization. The system is trained using all the available training data, without any specific technique for handling device mismatch, and obtains an overall accuracy of 47.7%, with a log loss of 1.473. Details on the challenge results will be added after the challenge deadline.

Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions

This paper presents the details of the Audio-Visual Scene Classification task in the DCASE 2021 Challenge (Task 1 Subtask B). The task is concerned with classification using audio and video modalities, using a dataset of synchronized recordings. Here we describe the datasets and baseline systems. After the challenge submission deadline, challenge results and analysis of the submissions will be added.

Active Learning for Sound Event Detection

This paper proposes an active learning system for sound event detection (SED). It aims at maximizing the accuracy of a learned SED model with limited annotation effort. The proposed system analyzes an initially unlabeled audio dataset, from which it selects sound segments for manual annotation. The candidate segments are generated based on a proposed change point detection approach, and the selection is based on the principle of mismatch-first farthest-traversal. During the training of SED models, recordings are used as training inputs, preserving the long-term context for annotated segments. The proposed system clearly outperforms reference methods in the two datasets used for evaluation (TUT Rare Sound 2017 and TAU Spatial Sound 2019). Training with recordings as context outperforms training with only annotated segments. Mismatch-first farthest-traversal outperforms reference sample selection methods based on random sampling and uncertainty sampling. Remarkably, the required annotation effort can be greatly reduced on the dataset where target sound events are rare: by annotating only 2% of the training data, the achieved SED performance is similar to annotating all the training data.

Acoustic Scene Classification: A Competition Review

In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the students and external participants. We identify the most suitable methods and study the impact of each by performing an ablation study of the mixture of approaches. We also compare the results with a neural network baseline, and show the improvement over that. Finally, we discuss the impact of using a competition as a part of a university course, and justify its importance in the curriculum based on student feedback.

Sound Event Detection in Multichannel Audio Using Spatial and Harmonic Features

In this paper, we propose the use of spatial and harmonic features in combination with long short term memory (LSTM) recurrent neural network (RNN) for automatic sound event detection (SED) task. Real life sound recordings typically have many overlapping sound events, making it hard to recognize with just mono channel audio. Human listeners have been successfully recognizing the mixture of overlapping sound events using pitch cues and exploiting the stereo (multichannel) audio signal available at their ears to spatially localize these events. Traditionally SED systems have only been using mono channel audio, motivated by the human listener we propose to extend them to use multichannel audio. The proposed SED system is compared against the state of the art mono channel method on the development subset of TUT sound events detection 2016 database. The usage of spatial and harmonic features are shown to improve the performance of SED.

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to local spectral and temporal variations. Recurrent neural networks (RNNs) are powerful in learning the longer term temporal context in the audio signals. CNNs and RNNs as classifiers have recently shown improved performances over established methods in various sound recognition tasks. We combine these two approaches in a Convolutional Recurrent Neural Network (CRNN) and apply it on a polyphonic sound event detection task. We compare the performance of the proposed CRNN method with CNN, RNN, and other established methods, and observe a considerable improvement for four different datasets consisting of everyday sound events.