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.
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.
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.
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.
In conventional studies on environmental sound separation and synthesis using captions, datasets consisting of multiple-source sounds with their captions were used for model training. However, when we collect the captions for multiple-source sound, it is not easy to collect detailed captions for each sound source, such as the number of sound occurrences and timbre. Therefore, it is difficult to extract only the single-source target sound by the model-training method using a conventional captioned sound dataset. In this work, we constructed a dataset with captions for a single-source sound named CAPTDURE, which can be used in various tasks such as environmental sound separation and synthesis. Our dataset consists of 1,044 sounds and 4,902 captions. We evaluated the performance of environmental sound extraction using our dataset. The experimental results show that the captions for single-source sounds are effective in extracting only the single-source target sound from the mixture sound.
We present the task description of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2023 Challenge Task 2: "First-shot unsupervised anomalous sound detection (ASD) for machine condition monitoring". The main goal is to enable rapid deployment of ASD systems for new kinds of machines using only a few normal samples, without the need for hyperparameter tuning. In the past ASD tasks, developed methods tuned hyperparameters for each machine type, as the development and evaluation datasets had the same machine types. However, collecting normal and anomalous data as the development dataset can be infeasible in practice. In 2023 Task 2, we focus on solving first-shot problem, which is the challenge of training a model on a few machines of a completely novel machine type. Specifically, (i) each machine type has only one section, and (ii) machine types in the development and evaluation datasets are completely different. We will add challenge results and analysis of the submissions after the challenge submission deadline.
One way of expressing an environmental sound is using vocal imitations, which involve the process of replicating or mimicking the rhythms and pitches of sounds by voice. We can effectively express the features of environmental sounds, such as rhythms and pitches, using vocal imitations, which cannot be expressed by conventional input information, such as sound event labels, images, and texts, in an environmental sound synthesis model. Therefore, using vocal imitations as input for environmental sound synthesis will enable us to control the pitches and rhythms of sounds and generate diverse sounds. In this paper, we thus propose a framework for environmental sound conversion from vocal imitations to generate diverse sounds. We also propose a method of environmental sound synthesis from vocal imitations and sound event labels. Using sound event labels is expected to control the sound event class of the synthesized sound, which cannot be controlled by only vocal imitations. Our objective and subjective experimental results show that vocal imitations effectively control the pitches and rhythms of sounds and generate diverse sounds.
The addition of Foley sound effects during post-production is a common technique used to enhance the perceived acoustic properties of multimedia content. Traditionally, Foley sound has been produced by human Foley artists, which involves manual recording and mixing of sound. However, recent advances in sound synthesis and generative models have generated interest in machine-assisted or automatic Foley synthesis techniques. To promote further research in this area, we have organized a challenge in DCASE 2023: Task 7 - Foley Sound Synthesis. Our challenge aims to provide a standardized evaluation framework that is both rigorous and efficient, allowing for the evaluation of different Foley synthesis systems. Through this challenge, we hope to encourage active participation from the research community and advance the state-of-the-art in automatic Foley synthesis. In this technical report, we provide a detailed overview of the Foley sound synthesis challenge, including task definition, dataset, baseline, evaluation scheme and criteria, and discussion.
We propose a method for synthesizing environmental sounds from visually represented onomatopoeias and sound sources. An onomatopoeia is a word that imitates a sound structure, i.e., the text representation of sound. From this perspective, onoma-to-wave has been proposed to synthesize environmental sounds from the desired onomatopoeia texts. Onomatopoeias have another representation: visual-text representations of sounds in comics, advertisements, and virtual reality. A visual onomatopoeia (visual text of onomatopoeia) contains rich information that is not present in the text, such as a long-short duration of the image, so the use of this representation is expected to synthesize diverse sounds. Therefore, we propose visual onoma-to-wave for environmental sound synthesis from visual onomatopoeia. The method can transfer visual concepts of the visual text and sound-source image to the synthesized sound. We also propose a data augmentation method focusing on the repetition of onomatopoeias to enhance the performance of our method. An experimental evaluation shows that the methods can synthesize diverse environmental sounds from visual text and sound-source images.
Although several methods of environmental sound synthesis have been proposed, there has been no discussion on how synthesized environmental sounds should be evaluated. Only either subjective or objective evaluations have been conducted in conventional evaluations, and it is not clear what type of evaluation should be carried out. In this paper, we investigate how to evaluate synthesized environmental sounds. We also propose a subjective evaluation methodology to evaluate whether the synthesized sound appropriately represents the information input to the environmental sound synthesis system. In our experiments, we compare the proposed and conventional evaluation methods and show that the results of subjective evaluations tended to differ from those of objective evaluations. From these results, we conclude that it is necessary to conduct not only objective evaluation but also subjective evaluation.