Self-Supervised Multi-View Learning for Disentangled Music Audio Representations

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view redundancy to create pretext tasks. However, these approaches often produce entangled representations and lose view-specific information. We propose a novel self-supervised multi-view learning framework for audio designed to incentivize separation between private and shared representation spaces. A case study on audio disentanglement in a controlled setting demonstrates the effectiveness of our method.

SONIQUE: Video Background Music Generation Using Unpaired Audio-Visual Data

We present SONIQUE, a model for generating background music tailored to video content. Unlike traditional video-to-music generation approaches, which rely heavily on paired audio-visual datasets, SONIQUE leverages unpaired data, combining royalty-free music and independent video sources. By utilizing large language models (LLMs) for video understanding and converting visual descriptions into musical tags, alongside a U-Net-based conditional diffusion model, SONIQUE enables customizable music generation. Users can control specific aspects of the music, such as instruments, genres, tempo, and melodies, ensuring the generated output fits their creative vision. SONIQUE is open-source, with a demo available online.

A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio

The task of Visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider positive examples without accounting for both positive and negative cases. In this paper, we introduce a novel test set and metrics designed to complete the current standard evaluation of VSSL models by testing them in scenarios where none of the objects in the image corresponds to the audio input, i.e. a negative audio. We consider three types of negative audio: silence, noise and offscreen. Our analysis reveals that numerous SOTA models fail to appropriately adjust their predictions based on audio input, suggesting that these models may not be leveraging audio information as intended. Additionally, we provide a comprehensive analysis of the range of maximum values in the estimated audio-visual similarity maps, in both positive and negative audio cases, and show that most of the models are not discriminative enough, making them unfit to choose a universal threshold appropriate to perform sound localization without any a priori information of the sounding object, that is, object size and visibility.

Two vs. Four-Channel Sound Event Localization and Detection

Sound event localization and detection (SELD) systems estimate both the direction-of-arrival (DOA) and class of sound sources over time. In the DCASE 2022 SELD Challenge (Task 3), models are designed to operate in a 4-channel setting. While beneficial to further the development of SELD systems using a multichannel recording setup such as first-order Ambisonics (FOA), most consumer electronics devices rarely are able to record using more than two channels. For this reason, in this work we investigate the performance of the DCASE 2022 SELD baseline model using three audio input representations: FOA, binaural, and stereo. We perform a novel comparative analysis illustrating the effect of these audio input representations on SELD performance. Crucially, we show that binaural and stereo (i.e. 2-channel) audio-based SELD models are still able to localize and detect sound sources laterally quite well, despite overall performance degrading as less audio information is provided. Further, we segment our analysis by scenes containing varying degrees of sound source polyphony to better understand the effect of audio input representation on localization and detection performance as scene conditions become increasingly complex.

Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions

Localizing a moving sound source in the real world involves determining its direction-of-arrival (DOA) and distance relative to a microphone. Advancements in DOA estimation have been facilitated by data-driven methods optimized with large open-source datasets with microphone array recordings in diverse environments. In contrast, estimating a sound source's distance remains understudied. Existing approaches assume recordings by non-coincident microphones to use methods that are susceptible to differences in room reverberation. We present a CRNN able to estimate the distance of moving sound sources across multiple datasets featuring diverse rooms, outperforming a recently-published approach. We also characterize our model's performance as a function of sound source distance and different training losses. This analysis reveals optimal training using a loss that weighs model errors as an inverse function of the sound source true distance. Our study is the first to demonstrate that sound source distance estimation can be performed across diverse acoustic conditions using deep learning.

Bridging High-Quality Audio and Video via Language for Sound Effects Retrieval from Visual Queries

Finding the right sound effects (SFX) to match moments in a video is a difficult and time-consuming task, and relies heavily on the quality and completeness of text metadata. Retrieving high-quality (HQ) SFX using a video frame directly as the query is an attractive alternative, removing the reliance on text metadata and providing a low barrier to entry for non-experts. Due to the lack of HQ audio-visual training data, previous work on audio-visual retrieval relies on YouTube (in-the-wild) videos of varied quality for training, where the audio is often noisy and the video of amateur quality. As such it is unclear whether these systems would generalize to the task of matching HQ audio to production-quality video. To address this, we propose a multimodal framework for recommending HQ SFX given a video frame by (1) leveraging large language models and foundational vision-language models to bridge HQ audio and video to create audio-visual pairs, resulting in a highly scalable automatic audio-visual data curation pipeline; and (2) using pre-trained audio and visual encoders to train a contrastive learning-based retrieval system. We show that our system, trained using our automatic data curation pipeline, significantly outperforms baselines trained on in-the-wild data on the task of HQ SFX retrieval for video. Furthermore, while the baselines fail to generalize to this task, our system generalizes well from clean to in-the-wild data, outperforming the baselines on a dataset of YouTube videos despite only being trained on the HQ audio-visual pairs. A user study confirms that people prefer SFX retrieved by our system over the baseline 67% of the time both for HQ and in-the-wild data. Finally, we present ablations to determine the impact of model and data pipeline design choices on downstream retrieval performance. Please visit our project website to listen to and view our SFX retrieval results.

A Multimodal Prototypical Approach for Unsupervised Sound Classification

In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio classification, but performance compared to supervised models remains limited. This work proposes a multimodal prototypical approach that exploits local audio-text embeddings to provide more relevant answers to audio queries, augmenting the adaptability of sound detection in the wild. We do this by first using text to query a nearby community of audio embeddings that best characterize each query sound, and select the group's centroids as our prototypes. Second, we compare unseen audio to these prototypes for classification. We perform multiple ablation studies to understand the impact of the embedding models and prompts. Our unsupervised approach improves upon the zero-shot state-of-the-art in three sound recognition benchmarks by an average of 12%.

Adapting Meter Tracking Models to Latin American Music

Beat and downbeat tracking models have improved significantly in recent years with the introduction of deep learning methods. However, despite these improvements, several challenges remain. Particularly, the adaptation of available models to underrepresented music traditions in MIR is usually synonymous with collecting and annotating large amounts of data, which is impractical and time-consuming. Transfer learning, data augmentation, and fine-tuning techniques have been used quite successfully in related tasks and are known to alleviate this bottleneck. Furthermore, when studying these music traditions, models are not required to generalize to multiple mainstream music genres but to perform well in more constrained, homogeneous conditions. In this work, we investigate simple yet effective strategies to adapt beat and downbeat tracking models to two different Latin American music traditions and analyze the feasibility of these adaptations in real-world applications concerning the data and computational requirements. Contrary to common belief, our findings show it is possible to achieve good performance by spending just a few minutes annotating a portion of the data and training a model in a standard CPU machine, with the precise amount of resources needed depending on the task and the complexity of the dataset.

Tempo vs. Pitch: understanding self-supervised tempo estimation

Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision, natural language processing, environmental sound analysis, and recently in music information retrieval, e.g. for pitch estimation. Particularly in the context of music, there are few insights about the fragility of these models regarding different distributions of data, and how they could be mitigated. In this paper, we explore these questions by dissecting a self-supervised model for pitch estimation adapted for tempo estimation via rigorous experimentation with synthetic data. Specifically, we study the relationship between the input representation and data distribution for self-supervised tempo estimation.

FlowGrad: Using Motion for Visual Sound Source Localization

Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal information present in videos. While it proves to be effective for widely used benchmark datasets, the method falls short for challenging scenarios like urban traffic. This work introduces temporal context into the state-of-the-art methods for sound source localization in urban scenes using optical flow as a means to encode motion information. An analysis of the strengths and weaknesses of our methods helps us better understand the problem of visual sound source localization and sheds light on open challenges for audio-visual scene understanding.