Learning to associate audio with textual descriptions is valuable for a range of tasks, including pretraining, zero-shot classification, audio retrieval, audio captioning, and text-conditioned audio generation. Existing contrastive language-audio pretrained models are typically trained using global, clip-level descriptions, which provide only weak temporal supervision. We hypothesize that CLAP-like language-audio models - particularly, if they are expected to produce frame-level embeddings - can benefit from a stronger temporal supervision. To confirm our hypothesis, we curate a novel dataset of approximately 12,000 audio recordings from Freesound, each annotated with single-sentence free-text descriptions linked to a specific temporal segment in an audio recording. We use large language models to clean these annotations by removing references to non-audible events, transcribed speech, typos, and annotator language bias. We further propose a frame-wise contrastive training strategy that learns to align text descriptions with temporal regions in an audio recording and demonstrate that our model has better temporal text-audio alignment abilities compared to models trained only on global captions when evaluated on the AudioSet Strong benchmark. The dataset and our source code are available on Zenodo and GitHub, respectively.

In this technical report, we describe the SNTL-NTU team's submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the detection and classification of acoustic scenes and events (DCASE) 2024 challenge. Three systems are introduced to tackle training splits of different sizes. For small training splits, we explored reducing the complexity of the provided baseline model by reducing the number of base channels. We introduce data augmentation in the form of mixup to increase the diversity of training samples. For the larger training splits, we use FocusNet to provide confusing class information to an ensemble of multiple Patchout faSt Spectrogram Transformer (PaSST) models and baseline models trained on the original sampling rate of 44.1 kHz. We use Knowledge Distillation to distill the ensemble model to the baseline student model. Training the systems on the TAU Urban Acoustic Scene 2022 Mobile development dataset yielded the highest average testing accuracy of (62.21, 59.82, 56.81, 53.03, 47.97)% on split (100, 50, 25, 10, 5)% respectively over the three systems.

Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two modalities end up close together. Since audio-caption datasets typically only contain matching pairs of recordings and descriptions, it has become common practice to create mismatching pairs by pairing the audio with a caption randomly drawn from the dataset. This is not ideal because the randomly sampled caption could, just by chance, partly or entirely describe the audio recording. However, correspondence information for all possible pairs is costly to annotate and thus typically unavailable; we, therefore, suggest substituting it with estimated correspondences. To this end, we propose a two-staged training procedure in which multiple retrieval models are first trained as usual, i.e., without estimated correspondences. In the second stage, the audio-caption correspondences predicted by these models then serve as prediction targets. We evaluate our method on the ClothoV2 and the AudioCaps benchmark and show that it improves retrieval performance, even in a restricting self-distillation setting where a single model generates and then learns from the estimated correspondences. We further show that our method outperforms the current state of the art by 1.6 pp. mAP@10 on the ClothoV2 benchmark.

Note alignment refers to the task of matching individual notes of two versions of the same symbolically encoded piece. Methods addressing this task commonly rely on sequence alignment algorithms such as Hidden Markov Models or Dynamic Time Warping (DTW) applied directly to note or onset sequences. While successful in many cases, such methods struggle with large mismatches between the versions. In this work, we learn note-wise representations from data augmented with various complex mismatch cases, e.g. repeats, skips, block insertions, and long trills. At the heart of our approach lies a transformer encoder network - TheGlueNote - which predicts pairwise note similarities for two 512 note subsequences. We postprocess the predicted similarities using flavors of weightedDTW and pitch-separated onsetDTW to retrieve note matches for two sequences of arbitrary length. Our approach performs on par with the state of the art in terms of note alignment accuracy, is considerably more robust to version mismatches, and works directly on any pair of MIDI files.

We propose a new graph convolutional block, called MusGConv, specifically designed for the efficient processing of musical score data and motivated by general perceptual principles. It focuses on two fundamental dimensions of music, pitch and rhythm, and considers both relative and absolute representations of these components. We evaluate our approach on four different musical understanding problems: monophonic voice separation, harmonic analysis, cadence detection, and composer identification which, in abstract terms, translate to different graph learning problems, namely, node classification, link prediction, and graph classification. Our experiments demonstrate that MusGConv improves the performance on three of the aforementioned tasks while being conceptually very simple and efficient. We interpret this as evidence that it is beneficial to include perception-informed processing of fundamental musical concepts when developing graph network applications on musical score data.

A range of applications of multi-modal music information retrieval is centred around the problem of connecting large collections of sheet music (images) to corresponding audio recordings, that is, identifying pairs of audio and score excerpts that refer to the same musical content. One of the typical and most recent approaches to this task employs cross-modal deep learning architectures to learn joint embedding spaces that link the two distinct modalities - audio and sheet music images. While there has been steady improvement on this front over the past years, a number of open problems still prevent large-scale employment of this methodology. In this article we attempt to provide an insightful examination of the current developments on audio-sheet music retrieval via deep learning methods. We first identify a set of main challenges on the road towards robust and large-scale cross-modal music retrieval in real scenarios. We then highlight the steps we have taken so far to address some of these challenges, documenting step-by-step improvement along several dimensions. We conclude by analysing the remaining challenges and present ideas for solving these, in order to pave the way to a unified and robust methodology for cross-modal music retrieval.

Many applications of cross-modal music retrieval are related to connecting sheet music images to audio recordings. A typical and recent approach to this is to learn, via deep neural networks, a joint embedding space that correlates short fixed-size snippets of audio and sheet music by means of an appropriate similarity structure. However, two challenges that arise out of this strategy are the requirement of strongly aligned data to train the networks, and the inherent discrepancies of musical content between audio and sheet music snippets caused by local and global tempo differences. In this paper, we address these two shortcomings by designing a cross-modal recurrent network that learns joint embeddings that can summarize longer passages of corresponding audio and sheet music. The benefits of our method are that it only requires weakly aligned audio-sheet music pairs, as well as that the recurrent network handles the non-linearities caused by tempo variations between audio and sheet music. We conduct a number of experiments on synthetic and real piano data and scores, showing that our proposed recurrent method leads to more accurate retrieval in all possible configurations.

This paper addresses the task of score following in sheet music given as unprocessed images. While existing work either relies on OMR software to obtain a computer-readable score representation, or crucially relies on prepared sheet image excerpts, we propose the first system that directly performs score following in full-page, completely unprocessed sheet images. Based on incoming audio and a given image of the score, our system directly predicts the most likely position within the page that matches the audio, outperforming current state-of-the-art image-based score followers in terms of alignment precision. We also compare our method to an OMR-based approach and empirically show that it can be a viable alternative to such a system.

A computer program is presented that learns to play piano with "expression" and that even won an international computer piano performance contest. A superficial analysis of an expressive performance generated by the system seems to suggest creative musical abilities. After a critical discussion of the processes underlying this behavior, we abandon the question of whether the system is really creative and turn to the true motivation that drives this research: to use AI methods to investigate and better understand music performance as a human creative behavior. A number of recent and current results from our research are briefly presented that indicate that machines can give us interesting insights into such a complex creative behavior, even if they may not be creative themselves. A computer program is to play two piano pieces that it has never seen before in an "expressive" way (that is, by shaping tempo, timing, dynamics, and articulation in such a way that the performances sound "musical" or "human").

The article introduces the reader to a large interdisciplinary research project whose goal is to use AI to gain new insight into a complex artistic phenomenon. We study fundamental principles of expressive music performance by measuring performance aspects in large numbers of recordings by highly skilled musicians (concert pianists) and analyzing the data with state-of-the-art methods from areas such as machine learning, data mining, and data visualization. The article first introduces the general research questions that guide the project and then summarizes some of the most important results achieved to date, with an emphasis on the most recent and still rather speculative work. A broad view of the discovery process is given, from data acquisition through data visualization to inductive model building and pattern discovery, and it turns out that AI plays an important role in all stages of such an ambitious enterprise. Our current results show that it is possible for machines to make novel and interesting discoveries even in a domain such as music and that even if we might never find the "Horowitz Factor," AI can give us completely new insights into complex artistic behavior.