Computer Audition: From Task-Specific Machine Learning to Foundation Models

Foundation models (FMs) are increasingly spearheading recent advances on a variety of tasks that fall under the purview of computer audition -- the use of machines to understand sounds. They feature several advantages over traditional pipelines: among others, the ability to consolidate multiple tasks in a single model, the option to leverage knowledge from other modalities, and the readily-available interaction with human users. Naturally, these promises have created substantial excitement in the audio community, and have led to a wave of early attempts to build new, general-purpose foundation models for audio. In the present contribution, we give an overview of computational audio analysis as it transitions from traditional pipelines towards auditory foundation models. Our work highlights the key operating principles that underpin those models, and showcases how they can accommodate multiple tasks that the audio community previously tackled separately.

Online Domain-Incremental Learning Approach to Classify Acoustic Scenes in All Locations

In this paper, we propose a method for online domain-incremental learning of acoustic scene classification from a sequence of different locations. Simply training a deep learning model on a sequence of different locations leads to forgetting of previously learned knowledge. In this work, we only correct the statistics of the Batch Normalization layers of a model using a few samples to learn the acoustic scenes from a new location without any excessive training. Experiments are performed on acoustic scenes from 11 different locations, with an initial task containing acoustic scenes from 6 locations and the remaining 5 incremental tasks each representing the acoustic scenes from a different location. The proposed approach outperforms fine-tuning based methods and achieves an average accuracy of 48.8% after learning the last task in sequence without forgetting acoustic scenes from the previously learned locations.

DCASE 2024 Task 4: Sound Event Detection with Heterogeneous Data and Missing Labels

The Detection and Classification of Acoustic Scenes and Events Challenge Task 4 aims to advance sound event detection (SED) systems in domestic environments by leveraging training data with different supervision uncertainty. Participants are challenged in exploring how to best use training data from different domains and with varying annotation granularity (strong/weak temporal resolution, soft/hard labels), to obtain a robust SED system that can generalize across different scenarios. Crucially, annotation across available training datasets can be inconsistent and hence sound labels of one dataset may be present but not annotated in the other one and vice-versa. As such, systems will have to cope with potentially missing target labels during training. Moreover, as an additional novelty, systems will also be evaluated on labels with different granularity in order to assess their robustness for different applications. To lower the entry barrier for participants, we developed an updated baseline system with several caveats to address these aforementioned problems. Results with our baseline system indicate that this research direction is promising and is possible to obtain a stronger SED system by using diverse domain training data with missing labels compared to training a SED system for each domain separately.

Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge

This article describes the Data-Efficient Low-Complexity Acoustic Scene Classification Task in the DCASE 2024 Challenge and the corresponding baseline system. The task setup is a continuation of previous editions (2022 and 2023), which focused on recording device mismatches and low-complexity constraints. This year's edition introduces an additional real-world problem: participants must develop data-efficient systems for five scenarios, which progressively limit the available training data. The provided baseline system is based on an efficient, factorized CNN architecture constructed from inverted residual blocks and uses Freq-MixStyle to tackle the device mismatch problem. The baseline system's accuracy ranges from 42.40% on the smallest to 56.99% on the largest training set.

Sound Event Detection and Localization with Distance Estimation

Sound Event Detection and Localization (SELD) is a combined task of identifying sound events and their corresponding direction-of-arrival (DOA). While this task has numerous applications and has been extensively researched in recent years, it fails to provide full information about the sound source position. In this paper, we overcome this problem by extending the task to Sound Event Detection, Localization with Distance Estimation (3D SELD). We study two ways of integrating distance estimation within the SELD core - a multi-task approach, in which the problem is tackled by a separate model output, and a single-task approach obtained by extending the multi-ACCDOA method to include distance information. We investigate both methods for the Ambisonic and binaural versions of STARSS23: Sony-TAU Realistic Spatial Soundscapes 2023. Moreover, our study involves experiments on the loss function related to the distance estimation part. Our results show that it is possible to perform 3D SELD without any degradation of performance in sound event detection and DOA estimation.

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.

Class-Incremental Learning for Multi-Label Audio Classification

In this paper, we propose a method for class-incremental learning of potentially overlapping sounds for solving a sequence of multi-label audio classification tasks. We design an incremental learner that learns new classes independently of the old classes. To preserve knowledge about the old classes, we propose a cosine similarity-based distillation loss that minimizes discrepancy in the feature representations of subsequent learners, and use it along with a Kullback-Leibler divergence-based distillation loss that minimizes discrepancy in their respective outputs. Experiments are performed on a dataset with 50 sound classes, with an initial classification task containing 30 base classes and 4 incremental phases of 5 classes each. After each phase, the system is tested for multi-label classification with the entire set of classes learned so far. The proposed method obtains an average F1-score of 40.9% over the five phases, ranging from 45.2% in phase 0 on 30 classes, to 36.3% in phase 4 on 50 classes. Average performance degradation over incremental phases is only 0.7 percentage points from the initial F1-score of 45.2%.

Evaluating Classification Systems Against Soft Labels with Fuzzy Precision and Recall

Classification systems are normally trained by minimizing the cross-entropy between system outputs and reference labels, which makes the Kullback-Leibler divergence a natural choice for measuring how closely the system can follow the data. Precision and recall provide another perspective for measuring the performance of a classification system. Non-binary references can arise from various sources, and it is often beneficial to use the soft labels for training instead of the binarized data. However, the existing definitions for precision and recall require binary reference labels, and binarizing the data can cause erroneous interpretations. We present a novel method to calculate precision, recall and F-score without quantizing the data. The proposed metrics extend the well established metrics as the definitions coincide when used with binary labels. To understand the behavior of the metrics we show simple example cases and an evaluation of different sound event detection models trained on real data with soft labels.

Training sound event detection with soft labels from crowdsourced annotations

In this paper, we study the use of soft labels to train a system for sound event detection (SED). Soft labels can result from annotations which account for human uncertainty about categories, or emerge as a natural representation of multiple opinions in annotation. Converting annotations to hard labels results in unambiguous categories for training, at the cost of losing the details about the labels distribution. This work investigates how soft labels can be used, and what benefits they bring in training a SED system. The results show that the system is capable of learning information about the activity of the sounds which is reflected in the soft labels and is able to detect sounds that are missed in the typical binary target training setup. We also release a new dataset produced through crowdsourcing, containing temporally strong labels for sound events in real-life recordings, with both soft and hard labels.

Incremental Learning of Acoustic Scenes and Sound Events

In this paper, we propose a method for incremental learning of two distinct tasks over time: acoustic scene classification (ASC) and audio tagging (AT). We use a simple convolutional neural network (CNN) model as an incremental learner to solve the tasks. Generally, incremental learning methods catastrophically forget the previous task when sequentially trained on a new task. To alleviate this problem, we use independent learning and knowledge distillation (KD) between the timesteps in learning. Experiments are performed on TUT 2016/2017 dataset, containing 4 acoustic scene classes and 25 sound event classes. The proposed incremental learner solves the AT task with an F1 score of 54.4% and the ASC task with an accuracy of 88.9% in an incremental time step, outperforming a multi-task system which solves ASC and AT at the same time. The ASC task performance degrades only by 5.1% from the initial time ASC accuracy of 94.0%.