DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection

This paper describes sound event localization and detection (SELD) for spatial audio recordings captured by firstorder ambisonics (FOA) microphones. In this task, one may train a deep neural network (DNN) using FOA data annotated with the classes and directions of arrival (DOAs) of sound events. However, the performance of this approach is severely bounded by the amount of annotated data. To overcome this limitation, we propose a novel method of pretraining the feature extraction part of the DNN in a self-supervised manner. We use spatial audio-visual recordings abundantly available as virtual reality contents. Assuming that sound objects are concurrently observed by the FOA microphones and the omni-directional camera, we jointly train audio and visual encoders with contrastive learning such that the audio and visual embeddings of the same recording and DOA are made close. A key feature of our method is that the DOA-wise audio embeddings are jointly extracted from the raw audio data, while the DOA-wise visual embeddings are separately extracted from the local visual crops centered on the corresponding DOA. This encourages the latent features of the audio encoder to represent both the classes and DOAs of sound events. The experiment using the DCASE2022 Task 3 dataset of 20 hours shows non-annotated audio-visual recordings of 100 hours reduced the error score of SELD from 36.4 pts to 34.9 pts.

Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation

Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fr\'echet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with larger models generally excelling but innovative lightweight approaches also showing promise. The strong correlation between objective metrics and human ratings validates our evaluation approach. We discuss outcomes in terms of audio quality, controllability, and architectural considerations for text-to-audio synthesizers, providing direction for future research.

Construction and Analysis of Impression Caption Dataset for Environmental Sounds

Some datasets with the described content and order of occurrence of sounds have been released for conversion between environmental sound and text. However, there are very few texts that include information on the impressions humans feel, such as "sharp" and "gorgeous," when they hear environmental sounds. In this study, we constructed a dataset with impression captions for environmental sounds that describe the impressions humans have when hearing these sounds. We used ChatGPT to generate impression captions and selected the most appropriate captions for sound by humans. Our dataset consists of 3,600 impression captions for environmental sounds. To evaluate the appropriateness of impression captions for environmental sounds, we conducted subjective and objective evaluations. From our evaluation results, we indicate that appropriate impression captions for environmental sounds can be generated.

LEAD Dataset: How Can Labels for Sound Event Detection Vary Depending on Annotators?

In this paper, we introduce a LargE-scale Annotator's labels for sound event Detection (LEAD) dataset, which is the dataset used to gain a better understanding of the variation in strong labels in sound event detection (SED). In SED, it is very time-consuming to collect large-scale strong labels, and in most cases, multiple workers divide up the annotations to create a single dataset. In general, strong labels created by multiple annotators have large variations in the type of sound events and temporal onset/offset. Through the annotations of multiple workers, uniquely determining the strong label is quite difficult because the dataset contains sounds that can be mistaken for similar classes and sounds whose temporal onset/offset is difficult to distinguish. If the strong labels of SED vary greatly depending on the annotator, the SED model trained on a dataset created by multiple annotators will be biased. Moreover, if annotators differ between training and evaluation data, there is a risk that the model cannot be evaluated correctly. To investigate the variation in strong labels, we release the LEAD dataset, which provides distinct strong labels for each clip annotated by 20 different annotators. The LEAD dataset allows us to investigate how strong labels vary from annotator to annotator and consider SED models that are robust to the variation of strong labels. The LEAD dataset consists of strong labels assigned to sound clips from TUT Sound Events 2016/2017, TUT Acoustic Scenes 2016, and URBAN-SED. We also analyze variations in the strong labels in the LEAD dataset and provide insights into the variations.

Description and Discussion on DCASE 2024 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring

We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge Task 2: First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring. Continuing from last year's DCASE 2023 Challenge Task 2, we organize the task as a first-shot problem under domain generalization required settings. The main goal of the first-shot problem is to enable rapid deployment of ASD systems for new kinds of machines without the need for machine-specific hyperparameter tunings. This problem setting was realized by (1) giving only one section for each machine type and (2) having completely different machine types for the development and evaluation datasets. For the DCASE 2024 Challenge Task 2, data of completely new machine types were newly collected and provided as the evaluation dataset. In addition, attribute information such as the machine operation conditions were concealed for several machine types to mimic situations where such information are unavailable. We will add challenge results and analysis of the submissions after the challenge submission deadline.

M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation

Contrastive language-audio pre-training (CLAP) enables zero-shot (ZS) inference of audio and exhibits promising performance in several classification tasks. However, conventional audio representations are still crucial for many tasks where ZS is not applicable (e.g., regression problems). Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning. To do so, we propose a new method, M2D-CLAP, which combines self-supervised learning Masked Modeling Duo (M2D) and CLAP. M2D learns an effective representation to model audio signals, and CLAP aligns the representation with text embedding. As a result, M2D-CLAP learns a versatile representation that allows for both ZS and transfer learning. Experiments show that M2D-CLAP performs well on linear evaluation, fine-tuning, and ZS classification with a GTZAN state-of-the-art of 75.17%, thus achieving a general-purpose audio-language representation.

Correlation of Fréchet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant

This paper explores whether considering alternative domain-specific embeddings to calculate the Fr\'echet Audio Distance (FAD) metric can help the FAD to correlate better with perceptual ratings of environmental sounds. We used embeddings from VGGish, PANNs, MS-CLAP, L-CLAP, and MERT, which are tailored for either music or environmental sound evaluation. The FAD scores were calculated for sounds from the DCASE 2023 Task 7 dataset. Using perceptual data from the same task, we find that PANNs-WGM-LogMel produces the best correlation between FAD scores and perceptual ratings of both audio quality and perceived fit with a Spearman correlation higher than 0.5. We also find that music-specific embeddings resulted in significantly lower results. Interestingly, VGGish, the embedding used for the original Fr\'echet calculation, yielded a correlation below 0.1. These results underscore the critical importance of the choice of embedding for the FAD metric design.

Discriminative Neighborhood Smoothing for Generative Anomalous Sound Detection

We propose discriminative neighborhood smoothing of generative anomaly scores for anomalous sound detection. While the discriminative approach is known to achieve better performance than generative approaches often, we have found that it sometimes causes significant performance degradation due to the discrepancy between the training and test data, making it less robust than the generative approach. Our proposed method aims to compensate for the disadvantages of generative and discriminative approaches by combining them. Generative anomaly scores are smoothed using multiple samples with similar discriminative features to improve the performance of the generative approach in an ensemble manner while keeping its robustness. Experimental results show that our proposed method greatly improves the original generative method, including absolute improvement of 22% in AUC and robustly works, while a discriminative method suffers from the discrepancy.

Refining Knowledge Transfer on Audio-Image Temporal Agreement for Audio-Text Cross Retrieval

The aim of this research is to refine knowledge transfer on audio-image temporal agreement for audio-text cross retrieval. To address the limited availability of paired non-speech audio-text data, learning methods for transferring the knowledge acquired from a large amount of paired audio-image data to shared audio-text representation have been investigated, suggesting the importance of how audio-image co-occurrence is learned. Conventional approaches in audio-image learning assign a single image randomly selected from the corresponding video stream to the entire audio clip, assuming their co-occurrence. However, this method may not accurately capture the temporal agreement between the target audio and image because a single image can only represent a snapshot of a scene, though the target audio changes from moment to moment. To address this problem, we propose two methods for audio and image matching that effectively capture the temporal information: (i) Nearest Match wherein an image is selected from multiple time frames based on similarity with audio, and (ii) Multiframe Match wherein audio and image pairs of multiple time frames are used. Experimental results show that method (i) improves the audio-text retrieval performance by selecting the nearest image that aligns with the audio information and transferring the learned knowledge. Conversely, method (ii) improves the performance of audio-image retrieval while not showing significant improvements in audio-text retrieval performance. These results indicate that refining audio-image temporal agreement may contribute to better knowledge transfer to audio-text retrieval.

F1-EV Score: Measuring the Likelihood of Estimating a Good Decision Threshold for Semi-Supervised Anomaly Detection

Anomalous sound detection (ASD) systems are usually compared by using threshold-independent performance measures such as AUC-ROC. However, for practical applications a decision threshold is needed to decide whether a given test sample is normal or anomalous. Estimating such a threshold is highly non-trivial in a semi-supervised setting where only normal training samples are available. In this work, F1-EV a novel threshold-independent performance measure for ASD systems that also includes the likelihood of estimating a good decision threshold is proposed and motivated using specific toy examples. In experimental evaluations, multiple performance measures are evaluated for all systems submitted to the ASD task of the DCASE Challenge 2023. It is shown that F1-EV is strongly correlated with AUC-ROC while having a significantly stronger correlation with the F1-score obtained with estimated and optimal decision thresholds than AUC-ROC.