Brian McFee

Keunwoo Choi, Sangshin Oh, Minsung Kang et al.

"Foley" refers to sound effects that are added to multimedia during post-production to enhance its perceived acoustic properties, e.g., by simulating the sounds of footsteps, ambient environmental sounds, or visible objects on the screen. While foley is traditionally produced by foley artists, there is increasing interest in automatic or machine-assisted techniques building upon recent advances in sound synthesis and generative models. To foster more participation in this growing research area, we propose a challenge for automatic foley synthesis. Through case studies on successful previous challenges in audio and machine learning, we set the goals of the proposed challenge: rigorous, unified, and efficient evaluation of different foley synthesis systems, with an overarching goal of drawing active participation from the research community. We outline the details and design considerations of a foley sound synthesis challenge, including task definition, dataset requirements, and evaluation criteria.

Chuyang Chen, Bea Steers, Brian McFee et al.

We propose a benchmark for evaluating compositionality in audio representations. Audio compositionality refers to representing sound scenes in terms of constituent sources and attributes, and combining them systematically. While central to auditory perception, this property is largely absent from current evaluation protocols. Our framework adapts ideas from vision and language to audio through two tasks: A-COAT, which tests consistency under additive transformations, and A-TRE, which probes reconstructibility from attribute-level primitives. Both tasks are supported by large synthetic datasets with controlled variation in acoustic attributes, providing the first benchmark of compositional structure in audio embeddings.

Jeffrey Tumminia, Amanda Kuznecov, Sophia Tsilerides et al.

United States Courts make audio recordings of oral arguments available as public record, but these recordings rarely include speaker annotations. This paper addresses the Speech Audio Diarization problem, answering the question of "Who spoke when?" in the domain of judicial oral argument proceedings. We present a workflow for diarizing the speech of judges using audio recordings of oral arguments, a process we call Reference-Dependent Speaker Verification. We utilize a speech embedding network trained with the Generalized End-to-End Loss to encode speech into d-vectors and a pre-defined reference audio library based on annotated data. We find that by encoding reference audio for speakers and full arguments and computing similarity scores we achieve a 13.8% Diarization Error Rate for speakers covered by the reference audio library on a held-out test set. We evaluate our method on the Supreme Court of the United States oral arguments, accessed through the Oyez Project, and outline future work for diarizing legal proceedings. A code repository for this research is available at github.com/JeffT13/rd-diarization

Junwon Lee, Modan Tailleur, Laurie M. Heller et al.

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 Fréchet 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.

Victor Deng, Changhong Wang, Gael Richard et al.

In recent years, foundation models have significantly advanced data-driven systems across various domains. Yet, their underlying properties, especially when functioning as feature extractors, remain under-explored. In this paper, we investigate the sensitivity to audio effects of audio embeddings extracted from widely-used foundation models, including OpenL3, PANNs, and CLAP. We focus on audio effects as the source of sensitivity due to their prevalent presence in large audio datasets. By applying parameterized audio effects (gain, low-pass filtering, reverberation, and bitcrushing), we analyze the correlation between the deformation trajectories and the effect strength in the embedding space. We propose to quantify the dimensionality and linearizability of the deformation trajectories induced by audio effects using canonical correlation analysis. We find that there exists a direction along which the embeddings move monotonically as the audio effect strength increases, but that the subspace containing the displacements is generally high-dimensional. This shows that pre-trained audio embeddings do not globally linearize the effects. Our empirical results on instrument classification downstream tasks confirm that projecting out the estimated deformation directions cannot generally improve the robustness of pre-trained embeddings to audio effects.

Mathieu Lagrange, Junwon Lee, Modan Tailleur et al.

This paper presents Task 7 at the DCASE 2024 Challenge: sound scene synthesis. Recent advances in sound synthesis and generative models have enabled the creation of realistic and diverse audio content. We introduce a standardized evaluation framework for comparing different sound scene synthesis systems, incorporating both objective and subjective metrics. The challenge attracted four submissions, which are evaluated using the Fréchet Audio Distance (FAD) and human perceptual ratings. Our analysis reveals significant insights into the current capabilities and limitations of sound scene synthesis systems, while also highlighting areas for future improvement in this rapidly evolving field.

Haokun Tian, Stefan Lattner, Brian McFee et al.

In traditional supervised learning, the cross-entropy loss treats all incorrect predictions equally, ignoring the relevance or proximity of wrong labels to the correct answer. By leveraging a tree hierarchy for fine-grained labels, we investigate hybrid losses, such as generalised triplet and cross-entropy losses, to enforce similarity between labels within a multi-task learning framework. We propose metrics to evaluate the embedding space structure and assess the model's ability to generalise to unseen classes, that is, to infer similar classes for data belonging to unseen categories. Our experiments on OrchideaSOL, a four-level hierarchical instrument sound dataset with nearly 200 detailed categories, demonstrate that the proposed hybrid losses outperform previous works in classification, retrieval, embedding space structure, and generalisation.

Iran R. Roman, Christopher Ick, Sivan Ding et al.

Sound event localization and detection (SELD) is an important task in machine listening. Major advancements rely on simulated data with sound events in specific rooms and strong spatio-temporal labels. SELD data is simulated by convolving spatialy-localized room impulse responses (RIRs) with sound waveforms to place sound events in a soundscape. However, RIRs require manual collection in specific rooms. We present SpatialScaper, a library for SELD data simulation and augmentation. Compared to existing tools, SpatialScaper emulates virtual rooms via parameters such as size and wall absorption. This allows for parameterized placement (including movement) of foreground and background sound sources. SpatialScaper also includes data augmentation pipelines that can be applied to existing SELD data. As a case study, we use SpatialScaper to add rooms to the DCASE SELD data. Training a model with our data led to progressive performance improves as a direct function of acoustic diversity. These results show that SpatialScaper is valuable to train robust SELD models.

Christopher Ick, Brian McFee

Recent literature has demonstrated that the use of per-channel energy normalization (PCEN), has significant performance improvements over traditional log-scaled mel-frequency spectrograms in acoustic sound event detection (SED) in a multi-class setting with overlapping events. However, the configuration of PCEN's parameters is sensitive to the recording environment, the characteristics of the class of events of interest, and the presence of multiple overlapping events. This leads to improvements on a class-by-class basis, but poor cross-class performance. In this article, we experiment using PCEN spectrograms as an alternative method for SED in urban audio using the UrbanSED dataset, demonstrating per-class improvements based on parameter configuration. Furthermore, we address cross-class performance with PCEN using a novel method, Multi-Rate PCEN (MRPCEN). We demonstrate cross-class SED performance with MRPCEN, demonstrating improvements to cross-class performance compared to traditional single-rate PCEN.

Ho-Hsiang Wu, Chieh-Chi Kao, Qingming Tang et al.

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and annotations for audio are time consuming and less intuitive. Besides, models learned from labeled dataset often embed biases specific to that particular dataset. Therefore, unsupervised learning techniques become popular approaches in solving machine listening problems. Particularly, a self-supervised learning technique utilizing reconstructions of multiple hand-crafted audio features has shown promising results when it is applied to speech domain such as emotion recognition and automatic speech recognition (ASR). In this paper, we apply self-supervised and multi-task learning methods for pre-training music encoders, and explore various design choices including encoder architectures, weighting mechanisms to combine losses from multiple tasks, and worker selections of pretext tasks. We investigate how these design choices interact with various downstream music classification tasks. We find that using various music specific workers altogether with weighting mechanisms to balance the losses during pre-training helps improve and generalize to the downstream tasks.

Helena Cuesta, Brian McFee, Emilia Gómez

This paper addresses the extraction of multiple F0 values from polyphonic and a cappella vocal performances using convolutional neural networks (CNNs). We address the major challenges of ensemble singing, i.e., all melodic sources are vocals and singers sing in harmony. We build upon an existing architecture to produce a pitch salience function of the input signal, where the harmonic constant-Q transform (HCQT) and its associated phase differentials are used as an input representation. The pitch salience function is subsequently thresholded to obtain a multiple F0 estimation output. For training, we build a dataset that comprises several multi-track datasets of vocal quartets with F0 annotations. This work proposes and evaluates a set of CNNs for this task in diverse scenarios and data configurations, including recordings with additional reverb. Our models outperform a state-of-the-art method intended for the same music genre when evaluated with an increased F0 resolution, as well as a general-purpose method for multi-F0 estimation. We conclude with a discussion on future research directions.

Vincent Lostanlen, Sripathi Sridhar, Brian McFee et al.

To explain the consonance of octaves, music psychologists represent pitch as a helix where azimuth and axial coordinate correspond to pitch class and pitch height respectively. This article addresses the problem of discovering this helical structure from unlabeled audio data. We measure Pearson correlations in the constant-Q transform (CQT) domain to build a K-nearest neighbor graph between frequency subbands. Then, we run the Isomap manifold learning algorithm to represent this graph in a three-dimensional space in which straight lines approximate graph geodesics. Experiments on isolated musical notes demonstrate that the resulting manifold resembles a helix which makes a full turn at every octave. A circular shape is also found in English speech, but not in urban noise. We discuss the impact of various design choices on the visualization: instrumentarium, loudness mapping function, and number of neighbors K.

Christopher J. Tralie, Brian McFee

We describe a novel pipeline to automatically discover hierarchies of repeated sections in musical audio. The proposed method uses similarity network fusion (SNF) to combine different frame-level features into clean affinity matrices, which are then used as input to spectral clustering. While prior spectral clustering approaches to music structure analysis have pre-processed affinity matrices with heuristics specifically designed for this task, we show that the SNF approach directly yields segmentations which agree better with human annotators, as measured by the ``L-measure'' metric for hierarchical annotations. Furthermore, the SNF approach immediately supports arbitrarily many input features, allowing us to simultaneously discover structure encoded in timbral, harmonic, and rhythmic representations without any changes to the base algorithm.

Rachel M. Bittner, Brian McFee, Juan P. Bello

Fundamental frequency (f0) estimation from polyphonic music includes the tasks of multiple-f0, melody, vocal, and bass line estimation. Historically these problems have been approached separately, and only recently, using learning-based approaches. We present a multitask deep learning architecture that jointly estimates outputs for various tasks including multiple-f0, melody, vocal and bass line estimation, and is trained using a large, semi-automatically annotated dataset. We show that the multitask model outperforms its single-task counterparts, and explore the effect of various design decisions in our approach, and show that it performs better or at least competitively when compared against strong baseline methods.

Brian McFee, Justin Salamon, Juan Pablo Bello

Sound event detection (SED) methods are tasked with labeling segments of audio recordings by the presence of active sound sources. SED is typically posed as a supervised machine learning problem, requiring strong annotations for the presence or absence of each sound source at every time instant within the recording. However, strong annotations of this type are both labor- and cost-intensive for human annotators to produce, which limits the practical scalability of SED methods. In this work, we treat SED as a multiple instance learning (MIL) problem, where training labels are static over a short excerpt, indicating the presence or absence of sound sources but not their temporal locality. The models, however, must still produce temporally dynamic predictions, which must be aggregated (pooled) when comparing against static labels during training. To facilitate this aggregation, we develop a family of adaptive pooling operators---referred to as auto-pool---which smoothly interpolate between common pooling operators, such as min-, max-, or average-pooling, and automatically adapt to the characteristics of the sound sources in question. We evaluate the proposed pooling operators on three datasets, and demonstrate that in each case, the proposed methods outperform non-adaptive pooling operators for static prediction, and nearly match the performance of models trained with strong, dynamic annotations. The proposed method is evaluated in conjunction with convolutional neural networks, but can be readily applied to any differentiable model for time-series label prediction.

Keunwoo Choi, George Fazekas, Brian McFee et al.

Descriptions are often provided along with recommendations to help users' discovery. Recommending automatically generated music playlists (e.g. personalised playlists) introduces the problem of generating descriptions. In this paper, we propose a method for generating music playlist descriptions, which is called as music captioning. In the proposed method, audio content analysis and natural language processing are adopted to utilise the information of each track.

Yonatan Vaizman, Brian McFee, Gert Lanckriet

Digital music has become prolific in the web in recent decades. Automated recommendation systems are essential for users to discover music they love and for artists to reach appropriate audience. When manual annotations and user preference data is lacking (e.g. for new artists) these systems must rely on \emph{content based} methods. Besides powerful machine learning tools for classification and retrieval, a key component for successful recommendation is the \emph{audio content representation}. Good representations should capture informative musical patterns in the audio signal of songs. These representations should be concise, to enable efficient (low storage, easy indexing, fast search) management of huge music repositories, and should also be easy and fast to compute, to enable real-time interaction with a user supplying new songs to the system. Before designing new audio features, we explore the usage of traditional local features, while adding a stage of encoding with a pre-computed \emph{codebook} and a stage of pooling to get compact vectorial representations. We experiment with different encoding methods, namely \emph{the LASSO}, \emph{vector quantization (VQ)} and \emph{cosine similarity (CS)}. We evaluate the representations' quality in two music information retrieval applications: query-by-tag and query-by-example. Our results show that concise representations can be used for successful performance in both applications. We recommend using top-$τ$ VQ encoding, which consistently performs well in both applications, and requires much less computation time than the LASSO.