Search

Progress in the task of symbolic music generation may be lagging behind other tasks like audio and text generation, in part because of the scarcity of symbolic training data. In this paper, we leverage the greater scale of audio music data by applying pre-trained MIR models (for transcription, beat tracking, structure analysis, etc.) to extract symbolic events and encode them into token sequences. To the best of our knowledge, this work is the first to demonstrate the feasibility of training symbolic generation models solely from auto-transcribed audio data. Furthermore, to enhance the controllability of the trained model, we introduce SymPAC (Symbolic Music Language Model with Prompting And Constrained Generation), which is distinguished by using (a) prompt bars in encoding and (b) a technique called Constrained Generation via Finite State Machines (FSMs) during inference time. We show the flexibility and controllability of this approach, which may be critical in making music AI useful to creators and users., Comment: ISMIR 2024

AIM To analyse the performance of a deep-learning (DL) algorithm currently deployed as diagnostic decision support software in two NHS Trusts used to identify normal chest x-rays in active clinical pathways. MATERIALS AND METHODS A DL algorithm has been deployed in Somerset NHS Foundation Trust (SFT) since December 2022, and at Calderdale & Huddersfield NHS Foundation Trust (CHFT) since March 2023. The algorithm was developed and trained prior to deployment, and is used to assign abnormality scores to each GP-requested chest x-ray (CXR). The algorithm classifies a subset of examinations with the lowest abnormality scores as High Confidence Normal (HCN), and displays this result to the Trust. This two-site study includes 4,654 CXR continuous examinations processed by the algorithm over a six-week period. RESULTS When classifying 20.0% of assessed examinations (930) as HCN, the model classified exams with a negative predictive value (NPV) of 0.96. There were 0.77% of examinations (36) classified incorrectly as HCN, with none of the abnormalities considered clinically significant by auditing radiologists. The DL software maintained fast levels of service to clinicians, with results returned to Trusts in a mean time of 7.1 seconds. CONCLUSION The DL algorithm performs with a low rate of error and is highly effective as an automated diagnostic decision support tool, used to autonomously report a subset of CXRs as normal with high confidence. Removing 20% of all CXRs reduces workload for reporters and allows radiology departments to focus resources elsewhere., Comment: 7 pages, 5 figures, 2 tables. Submitted to Clinical Radiology

Creating a pop song melody according to pre-written lyrics is a typical practice for composers. A computational model of how lyrics are set as melodies is important for automatic composition systems, but an end-to-end lyric-to-melody model would require enormous amounts of paired training data. To mitigate the data constraints, we adopt a two-stage approach, dividing the task into lyric-to-rhythm and rhythm-to-melody modules. However, the lyric-to-rhythm task is still challenging due to its multimodality. In this paper, we propose a novel lyric-to-rhythm framework that includes part-of-speech tags to achieve better text setting, and a Transformer architecture designed to model long-term syllable-to-note associations. For the rhythm-to-melody task, we adapt a proven chord-conditioned melody Transformer, which has achieved state-of-the-art results. Experiments for Chinese lyric-to-melody generation show that the proposed framework is able to model key characteristics of rhythm and pitch distributions in the dataset, and in a subjective evaluation, the melodies generated by our system were rated as similar to or better than those of a state-of-the-art alternative., Comment: Published in ISMIR 2022

Music structure analysis (MSA) systems aim to segment a song recording into non-overlapping sections with useful labels. Previous MSA systems typically predict abstract labels in a post-processing step and require the full context of the song. By contrast, we recently proposed a supervised framework, called "Music Structural Function Analysis" (MuSFA), that models and predicts meaningful labels like 'verse' and 'chorus' directly from audio, without requiring the full context of a song. However, the performance of this system depends on the amount and quality of training data. In this paper, we propose to repurpose a public dataset, HookTheory Lead Sheet Dataset (HLSD), to improve the performance. HLSD contains over 18K excerpts of music sections originally collected for studying automatic melody harmonization. We treat each excerpt as a partially labeled song and provide a label mapping, so that HLSD can be used together with other public datasets, such as SALAMI, RWC, and Isophonics. In cross-dataset evaluations, we find that including HLSD in training can improve state-of-the-art boundary detection and section labeling scores by ~3% and ~1% respectively., Comment: ISMIR2022, LBD paper

Purpose: Artificial intelligence (AI) solutions for medical diagnosis require thorough evaluation to demonstrate that performance is maintained for all patient sub-groups and to ensure that proposed improvements in care will be delivered equitably. This study evaluates the robustness of an AI solution for the diagnosis of normal chest X-rays (CXRs) by comparing performance across multiple patient and environmental subgroups, as well as comparing AI errors with those made by human experts. Methods: A total of 4,060 CXRs were sampled to represent a diverse dataset of NHS patients and care settings. Ground-truth labels were assigned by a 3-radiologist panel. AI performance was evaluated against assigned labels and sub-groups analysis was conducted against patient age and sex, as well as CXR view, modality, device manufacturer and hospital site. Results: The AI solution was able to remove 18.5% of the dataset by classification as High Confidence Normal (HCN). This was associated with a negative predictive value (NPV) of 96.0%, compared to 89.1% for diagnosis of normal scans by radiologists. In all AI false negative (FN) cases, a radiologist was found to have also made the same error when compared to final ground-truth labels. Subgroup analysis showed no statistically significant variations in AI performance, whilst reduced normal classification was observed in data from some hospital sites. Conclusion: We show the AI solution could provide meaningful workload savings by diagnosis of 18.5% of scans as HCN with a superior NPV to human readers. The AI solution is shown to perform well across patient subgroups and error cases were shown to be subjective or subtle in nature.

Objectives: The present study evaluated the impact of a commercially available explainable AI algorithm in augmenting the ability of clinicians to identify lung cancer on chest X-rays (CXR). Design: This retrospective study evaluated the performance of 11 clinicians for detecting lung cancer from chest radiographs, with and without assistance from a commercially available AI algorithm (red dot, Behold.ai) that predicts suspected lung cancer from CXRs. Clinician performance was evaluated against clinically confirmed diagnoses. Setting: The study analysed anonymised patient data from an NHS hospital; the dataset consisted of 400 chest radiographs from adult patients (18 years and above) who had a CXR performed in 2020, with corresponding clinical text reports. Participants: A panel of readers consisting of 11 clinicians (consultant radiologists, radiologist trainees and reporting radiographers) participated in this study. Main outcome measures: Overall accuracy, sensitivity, specificity and precision for detecting lung cancer on CXRs by clinicians, with and without AI input. Agreement rates between clinicians and performance standard deviation were also evaluated, with and without AI input. Results: The use of the AI algorithm by clinicians led to an improved overall performance for lung tumour detection, achieving an overall increase of 17.4% of lung cancers being identified on CXRs which would have otherwise been missed, an overall increase in detection of smaller tumours, a 24% and 13% increased detection of stage 1 and stage 2 lung cancers respectively, and standardisation of clinician performance. Conclusions: This study showed great promise in the clinical utility of AI algorithms in improving early lung cancer diagnosis and promoting health equity through overall improvement in reader performances, without impacting downstream imaging resources.

Conventional music structure analysis algorithms aim to divide a song into segments and to group them with abstract labels (e.g., 'A', 'B', and 'C'). However, explicitly identifying the function of each segment (e.g., 'verse' or 'chorus') is rarely attempted, but has many applications. We introduce a multi-task deep learning framework to model these structural semantic labels directly from audio by estimating "verseness," "chorusness," and so forth, as a function of time. We propose a 7-class taxonomy (i.e., intro, verse, chorus, bridge, outro, instrumental, and silence) and provide rules to consolidate annotations from four disparate datasets. We also propose to use a spectral-temporal Transformer-based model, called SpecTNT, which can be trained with an additional connectionist temporal localization (CTL) loss. In cross-dataset evaluations using four public datasets, we demonstrate the effectiveness of the SpecTNT model and CTL loss, and obtain strong results overall: the proposed system outperforms state-of-the-art chorus-detection and boundary-detection methods at detecting choruses and boundaries, respectively., Comment: This manuscript is accepted by ICASSP 2022

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used to elicit these patterns. However, with more annotations of section labels (e.g., verse, chorus, and bridge) becoming available, one can use supervised feature learning to make these patterns even clearer and improve MSA performance. To this end, we take a supervised metric learning approach: we train a deep neural network to output embeddings that are near each other for two spectrogram inputs if both have the same section type (according to an annotation), and otherwise far apart. We propose a batch sampling scheme to ensure the labels in a training pair are interpreted meaningfully. The trained model extracts features that can be used in existing MSA algorithms. In evaluations with three datasets (HarmonixSet, SALAMI, and RWC), we demonstrate that using the proposed features can improve a traditional MSA algorithm significantly in both intra- and cross-dataset scenarios., Comment: This paper was accepted and presented at ISMIR 2021

This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised, with pipelines designed to target some quality that is assumed to define "chorusness," which usually means seeking the loudest or most frequently repeated sections. We propose to use a convolutional neural network with a multi-task learning objective, which simultaneously fits two temporal activation curves: one indicating "chorusness" as a function of time, and the other the location of the boundaries. We also propose a post-processing method that jointly takes into account the chorus and boundary predictions to produce binary output. In experiments using three datasets, we compare our system to a set of public implementations of other segmentation and chorus-detection algorithms, and find our approach performs significantly better., Comment: This version is a preprint of an accepted paper by ICASSP2021. Please cite the publication in the Proceedings of IEEE International Conference on Acoustics, Speech, & Signal Processing

A music mashup combines audio elements from two or more songs to create a new work. To reduce the time and effort required to make them, researchers have developed algorithms that predict the compatibility of audio elements. Prior work has focused on mixing unaltered excerpts, but advances in source separation enable the creation of mashups from isolated stems (e.g., vocals, drums, bass, etc.). In this work, we take advantage of separated stems not just for creating mashups, but for training a model that predicts the mutual compatibility of groups of excerpts, using self-supervised and semi-supervised methods. Specifically, we first produce a random mashup creation pipeline that combines stem tracks obtained via source separation, with key and tempo automatically adjusted to match, since these are prerequisites for high-quality mashups. To train a model to predict compatibility, we use stem tracks obtained from the same song as positive examples, and random combinations of stems with key and/or tempo unadjusted as negative examples. To improve the model and use more data, we also train on "average" examples: random combinations with matching key and tempo, where we treat them as unlabeled data as their true compatibility is unknown. To determine whether the combined signal or the set of stem signals is more indicative of the quality of the result, we experiment on two model architectures and train them using semi-supervised learning technique. Finally, we conduct objective and subjective evaluations of the system, comparing them to a standard rule-based system., Comment: This is a preprint of the paper accepted by AAAI-21. Please cite the version included in the Proceedings of the 35th AAAI Conference on Artificial Intelligence

Understanding the mechanisms underlying general anesthesia would be a key step towards understanding consciousness. The process of xenon-induced general anesthesia has been shown to involve electron transfer, and the potency of xenon as a general anesthetic exhibits isotopic dependence. We propose that these observations can be explained by a mechanism in which the xenon nuclear spin influences the recombination dynamics of a naturally occurring radical pair of electrons. We develop a simple model inspired by the body of work on the radical-pair mechanism in cryptochrome in the context of avian magnetoreception, and we show that our model can reproduce the observed isotopic dependence of the general anesthetic potency of xenon in mice. Our results are consistent with the idea that radical pairs of electrons with entangled spins could be important for consciousness., Comment: 17 pages, 10 figures

Music loops are essential ingredients in electronic music production, and there is a high demand for pre-recorded loops in a variety of styles. Several commercial and community databases have been created to meet this demand, but most are not suitable for research due to their strict licensing. We present the Freesound Loop Dataset (FSLD), a new large-scale dataset of music loops annotated by experts. The loops originate from Freesound, a community database of audio recordings released under Creative Commons licenses, so the audio in our dataset may be redistributed. The annotations include instrument, tempo, meter, key and genre tags. We describe the methodology used to assemble and annotate the data, and report on the distribution of tags in the data and inter-annotator agreement. We also present to the community an online loop annotator tool that we developed. To illustrate the usefulness of FSLD, we present short case studies on using it to estimate tempo and key, generate music tracks, and evaluate a loop separation algorithm. We anticipate that the community will find yet more uses for the data, in applications from automatic loop characterisation to algorithmic composition., Comment: This work will be presented in the 21st International Society for Music Information Retrieval (ISMIR2020). Annotator website: http://mtg.upf.edu/fslannotator Dataset: https://zenodo.org/record/3967852

Music producers who use loops may have access to thousands in loop libraries, but finding ones that are compatible is a time-consuming process; we hope to reduce this burden with automation. State-of-the-art systems for estimating compatibility, such as AutoMashUpper, are mostly rule-based and could be improved on with machine learn-ing. To train a model, we need a large set of loops with ground truth compatibility values. No such dataset exists, so we extract loops from existing music to obtain positive examples of compatible loops, and propose and compare various strategies for choosing negative examples. For re-producibility, we curate data from the Free Music Archive.Using this data, we investigate two types of model architectures for estimating the compatibility of loops: one based on a Siamese network, and the other a pure convolutional neural network (CNN). We conducted a user study in which participants rated the quality of the combinations suggested by each model, and found the CNN to outperform the Siamese network. Both model-based approaches outperformed the rule-based one. We have opened source the code for building the models and the dataset., Comment: Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020)