Search

In this paper, we study a series of algorithmic problems related to the subsequences occurring in the strings of a given language, under the assumption that this language is succinctly represented by a grammar generating it, or an automaton accepting it. In particular, we focus on the following problems: Given a string $w$ and a language $L$, does there exist a word of $L$ which has $w$ as subsequence? Do all words of $L$ have $w$ as a subsequence? Given an integer $k$ alongside $L$, does there exist a word of $L$ which has all strings of length $k$, over the alphabet of $L$, as subsequences? Do all words of $L$ have all strings of length $k$ as subsequences? For the last two problems, efficient algorithms were already presented in [Adamson et al., ISAAC 2023] for the case when $L$ is a regular language, and efficient solutions can be easily obtained for the first two problems. We extend that work as follows: we give sufficient conditions on the class of input-languages, under which these problems are decidable; we provide efficient algorithms for all these problems in the case when the input language is context-free; we show that all problems are undecidable for context-sensitive languages. Finally, we provide a series of initial results related to a class of languages that strictly includes the regular languages and is strictly included in the class of context-sensitive languages, but is incomparable to the of class context-free languages; these results deviate significantly from those reported for language-classes from the Chomsky hierarchy., Comment: Abstract to be published in the proceedings of ISAAC 2024

Data augmentation plays a crucial role in addressing the challenge of limited expert-annotated datasets in deep learning applications for retinal Optical Coherence Tomography (OCT) scans. This work exhaustively investigates the impact of various data augmentation techniques on retinal layer boundary and fluid segmentation. Our results reveal that their effectiveness significantly varies based on the dataset's characteristics and the amount of available labeled data. While the benefits of augmentation are not uniform - being more pronounced in scenarios with scarce data, particularly for transformation-based methods - the findings highlight the necessity of a strategic approach to data augmentation. It is essential to note that the effectiveness of data augmentation varies significantly depending on the characteristics of the dataset. The findings emphasize the need for a nuanced approach, considering factors like dataset characteristics, the amount of labelled data, and the choice of model architecture.

This paper presents Tidal-MerzA, a novel system designed for collaborative performances between humans and a machine agent in the context of live coding, specifically focusing on the generation of musical patterns. Tidal-MerzA fuses two foundational models: ALCAA (Affective Live Coding Autonomous Agent) and Tidal Fuzz, a computational framework. By integrating affective modelling with computational generation, this system leverages reinforcement learning techniques to dynamically adapt music composition parameters within the TidalCycles framework, ensuring both affective qualities to the patterns and syntactical correctness. The development of Tidal-MerzA introduces two distinct agents: one focusing on the generation of mini-notation strings for musical expression, and another on the alignment of music with targeted affective states through reinforcement learning. This approach enhances the adaptability and creative potential of live coding practices and allows exploration of human-machine creative interactions. Tidal-MerzA advances the field of computational music generation, presenting a novel methodology for incorporating artificial intelligence into artistic practices.

This paper proposes a control technique for autonomous RC car racing. The presented method does not require any map-building phase beforehand since it operates only local path planning on the actual LiDAR point cloud. Racing control algorithms must have the capability to be optimized to the actual track layout for minimization of lap time. In the examined one, it is guaranteed with the improvement of the Stanley controller with additive control components to stabilize the movement in both low and high-speed ranges, and with the integration of an adaptive lookahead point to induce sharp and dynamic cornering for traveled distance reduction. The developed method is tested on a 1/10-sized RC car, and the tuning procedure from a base solution to the optimal setting in a real F1Tenth race is presented. Furthermore, the proposed method is evaluated with a comparison to a more simple reactive method, and in parallel to a more complex optimization-based technique that involves offline map building the global optimal trajectory calculation. The performance of the proposed method compared to the latter, referring to the lap time, is that the proposed one has only 8% lower average speed. This demonstrates that with appropriate tuning, a local planning-based method can be comparable with a more complex optimization-based one. Thus, the performance gap is lower than 10% from the state-of-the-art method. Moreover, the proposed technique has significantly higher similarity to real scenarios, therefore the results can be interesting in the context of automotive industry.

Optical Music Recognition (OMR) automates the transcription of musical notation from images into machine-readable formats like MusicXML, MEI, or MIDI, significantly reducing the costs and time of manual transcription. This study explores knowledge discovery in OMR by applying instance segmentation using Mask R-CNN to enhance the detection and delineation of musical symbols in sheet music. Unlike Optical Character Recognition (OCR), OMR must handle the intricate semantics of Common Western Music Notation (CWMN), where symbol meanings depend on shape, position, and context. Our approach leverages instance segmentation to manage the density and overlap of musical symbols, facilitating more precise information retrieval from music scores. Evaluations on the DoReMi and MUSCIMA++ datasets demonstrate substantial improvements, with our method achieving a mean Average Precision (mAP) of up to 59.70\% in dense symbol environments, achieving comparable results to object detection. Furthermore, using traditional computer vision techniques, we add a parallel step for staff detection to infer the pitch for the recognised symbols. This study emphasises the role of pixel-wise segmentation in advancing accurate music symbol recognition, contributing to knowledge discovery in OMR. Our findings indicate that instance segmentation provides more precise representations of musical symbols, particularly in densely populated scores, advancing OMR technology. We make our implementation, pre-processing scripts, trained models, and evaluation results publicly available to support further research and development., Comment: 8 pages content and one references, accepted version at the International Conference on Knowledge Discovery and Information Retrieval 2024, Porto, Portugal

In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This comprehensive review examines state-of-the-art (SOTA) pre-trained models and foundation models in music, spanning from representation learning, generative learning and multimodal learning. We first contextualise the significance of music in various industries and trace the evolution of AI in music. By delineating the modalities targeted by foundation models, we discover many of the music representations are underexplored in FM development. Then, emphasis is placed on the lack of versatility of previous methods on diverse music applications, along with the potential of FMs in music understanding, generation and medical application. By comprehensively exploring the details of the model pre-training paradigm, architectural choices, tokenisation, finetuning methodologies and controllability, we emphasise the important topics that should have been well explored, like instruction tuning and in-context learning, scaling law and emergent ability, as well as long-sequence modelling etc. A dedicated section presents insights into music agents, accompanied by a thorough analysis of datasets and evaluations essential for pre-training and downstream tasks. Finally, by underscoring the vital importance of ethical considerations, we advocate that following research on FM for music should focus more on such issues as interpretability, transparency, human responsibility, and copyright issues. The paper offers insights into future challenges and trends on FMs for music, aiming to shape the trajectory of human-AI collaboration in the music realm.

Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by leveraging consistency models. Music2Latent encodes samples into a compressed continuous latent space in a single end-to-end training process while enabling high-fidelity single-step reconstruction. Key innovations include conditioning the consistency model on upsampled encoder outputs at all levels through cross connections, using frequency-wise self-attention to capture long-range frequency dependencies, and employing frequency-wise learned scaling to handle varying value distributions across frequencies at different noise levels. We demonstrate that Music2Latent outperforms existing continuous audio autoencoders in sound quality and reconstruction accuracy while achieving competitive performance on downstream MIR tasks using its latent representations. To our knowledge, this represents the first successful attempt at training an end-to-end consistency autoencoder model., Comment: Accepted to ISMIR 2024

Multimodal models that jointly process audio and language hold great promise in audio understanding and are increasingly being adopted in the music domain. By allowing users to query via text and obtain information about a given audio input, these models have the potential to enable a variety of music understanding tasks via language-based interfaces. However, their evaluation poses considerable challenges, and it remains unclear how to effectively assess their ability to correctly interpret music-related inputs with current methods. Motivated by this, we introduce MuChoMusic, a benchmark for evaluating music understanding in multimodal language models focused on audio. MuChoMusic comprises 1,187 multiple-choice questions, all validated by human annotators, on 644 music tracks sourced from two publicly available music datasets, and covering a wide variety of genres. Questions in the benchmark are crafted to assess knowledge and reasoning abilities across several dimensions that cover fundamental musical concepts and their relation to cultural and functional contexts. Through the holistic analysis afforded by the benchmark, we evaluate five open-source models and identify several pitfalls, including an over-reliance on the language modality, pointing to a need for better multimodal integration. Data and code are open-sourced., Comment: Accepted at ISMIR 2024. Data: https://doi.org/10.5281/zenodo.12709974 Code: https://github.com/mulab-mir/muchomusic Supplementary material: https://mulab-mir.github.io/muchomusic

Despite the success of contrastive learning in Music Information Retrieval, the inherent ambiguity of contrastive self-supervision presents a challenge. Relying solely on augmentation chains and self-supervised positive sampling strategies can lead to a pretraining objective that does not capture key musical information for downstream tasks. We introduce semi-supervised contrastive learning (SemiSupCon), a simple method for leveraging musically informed labeled data (supervision signals) in the contrastive learning of musical representations. Our approach introduces musically relevant supervision signals into self-supervised contrastive learning by combining supervised and self-supervised contrastive objectives in a simpler framework than previous approaches. This framework improves downstream performance and robustness to audio corruptions on a range of downstream MIR tasks with moderate amounts of labeled data. Our approach enables shaping the learned similarity metric through the choice of labeled data that (1) infuses the representations with musical domain knowledge and (2) improves out-of-domain performance with minimal general downstream performance loss. We show strong transfer learning performance on musically related yet not trivially similar tasks - such as pitch and key estimation. Additionally, our approach shows performance improvement on automatic tagging over self-supervised approaches with only 5\% of available labels included in pretraining., Comment: Accepted to be published at the Proceedings of the 25th International Society for Music Information Retrieval Conference 2024, Includes non-proceedings appendix

Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for mixing style transfer are limited in that they often operate only on a fixed number of tracks, introduce artifacts, and produce mixes in an end-to-end fashion, without grounding in traditional audio effects, prohibiting interpretability and controllability. To overcome these challenges, we introduce Diff-MST, a framework comprising a differentiable mixing console, a transformer controller, and an audio production style loss function. By inputting raw tracks and a reference song, our model estimates control parameters for audio effects within a differentiable mixing console, producing high-quality mixes and enabling post-hoc adjustments. Moreover, our architecture supports an arbitrary number of input tracks without source labelling, enabling real-world applications. We evaluate our model's performance against robust baselines and showcase the effectiveness of our approach, architectural design, tailored audio production style loss, and innovative training methodology for the given task., Comment: Accepted to be published at the Proceedings of the 25th International Society for Music Information Retrieval Conference 2024

We introduce and study a generalized Parikh matrix mapping based on tracking the occurrence counts of special types of subsequences. These matrices retain more information about a word than the original Parikh matrix mapping while preserving the homomorphic property. We build the generalization by first introducing the Parikh factor matrix mapping and extend it to the Parikh sequence matrix mapping. We establish an interesting connection between the generalized Parikh matrices and the original ones and use it to prove that certain important minors of a Parikh sequence matrix have nonnegative determinant. Finally, we generalize the concept of subword histories and show that each generalized subword history is equivalent to a linear one.

Training the linear prediction (LP) operator end-to-end for audio synthesis in modern deep learning frameworks is slow due to its recursive formulation. In addition, frame-wise approximation as an acceleration method cannot generalise well to test time conditions where the LP is computed sample-wise. Efficient differentiable sample-wise LP for end-to-end training is the key to removing this barrier. We generalise the efficient time-invariant LP implementation from the GOLF vocoder to time-varying cases. Combining this with the classic source-filter model, we show that the improved GOLF learns LP coefficients and reconstructs the voice better than its frame-wise counterparts. Moreover, in our listening test, synthesised outputs from GOLF scored higher in quality ratings than the state-of-the-art differentiable WORLD vocoder., Comment: Published at Interspeech 2024

In binaural audio synthesis, aligning head-related impulse responses (HRIRs) in time has been an important pre-processing step, enabling accurate spatial interpolation and efficient data compression. The maximum correlation time delay between spatially nearby HRIRs has previously been used to get accurate and smooth alignment by solving a matrix equation in which the solution has the minimum Euclidean distance to the time delay. However, the Euclidean criterion could lead to an over-smoothing solution in practice. In this paper, we solve the smoothing issue by formulating the task as solving an integer linear programming problem equivalent to minimising an $L^1$-norm. Moreover, we incorporate 1) the cross-correlation of inter-aural HRIRs, and 2) HRIRs with their minimum-phase responses to have more reference measurements for optimisation. We show the proposed method can get more accurate alignments than the Euclidean-based method by comparing the spectral reconstruction loss of time-aligned HRIRs using spherical harmonics representation on seven HRIRs consisting of human and dummy heads. The extra correlation features and the $L^1$-norm are also beneficial in extremely noisy conditions. In addition, this method can be applied to phase unwrapping of head-related transfer functions, where the unwrapped phase could be a compact feature for downstream tasks., Comment: Published at Audio Engineering Society 156th Convention, 2024 June, Madrid, Spain

Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these systems using automatic differentiation. Although non-recursive filter approximations like frequency sampling and frame-based processing have been proposed and widely used in previous works, they cannot accurately reflect the gradient of the original system. We alleviate this difficulty by re-expressing a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks. This implementation can be employed within audio systems containing filters with poles for efficient gradient evaluation. We demonstrate its training efficiency and expressive capabilities for modelling real-world dynamic audio systems on a phaser, time-varying subtractive synthesiser, and compressor. We make our code and audio samples available and provide the trained audio effect and synth models in a VST plugin at https://diffapf.github.io/web/., Comment: Published at DAFx 2024

In this paper, sequences of trials having three outcomes are studied. The outcomes are labelled as success, failure of type I and failure of type II. A run is called at most 1+1 contaminated, if it contains at most 1 failure of type I and at most 1 failure of type II. The limiting distribution of the first hitting time and the accompanying distribution for the length of the longest at most 1+1 contaminated run are obtained. This paper contains the detailed mathematical proofs. Simulation results supporting the theorems are also presented., Comment: 25 pages, 8 figures

K-fold cross-validation is a widely used tool for assessing classifier performance. The reproducibility crisis faced by artificial intelligence partly results from the irreproducibility of reported k-fold cross-validation-based performance scores. Recently, we introduced numerical techniques to test the consistency of claimed performance scores and experimental setups. In a crucial use case, the method relies on the combinatorial enumeration of all k-fold configurations, for which we proposed an algorithm in the binary classification case.

Music source separation is focused on extracting distinct sonic elements from composite tracks. Historically, many methods have been grounded in supervised learning, necessitating labeled data, which is occasionally constrained in its diversity. More recent methods have delved into N-shot techniques that utilize one or more audio samples to aid in the separation. However, a challenge with some of these methods is the necessity for an audio query during inference, making them less suited for genres with varied timbres and effects. This paper offers a proof-of-concept for a self-supervised music source separation system that eliminates the need for audio queries at inference time. In the training phase, while it adopts a query-based approach, we introduce a modification by substituting the continuous embedding of query audios with Vector Quantized (VQ) representations. Trained end-to-end with up to N classes as determined by the VQ's codebook size, the model seeks to effectively categorise instrument classes. During inference, the input is partitioned into N sources, with some potentially left unutilized based on the mix's instrument makeup. This methodology suggests an alternative avenue for considering source separation across diverse music genres. We provide examples and additional results online., Comment: 4 pages, 2 figures, 1 table; Accepted at the 37th Conference on Neural Information Processing Systems (2023), Machine Learning for Audio Workshop

We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality audio-caption pairs, designed for the evaluation of music-and-language models. The dataset consists of 1.1k human-written natural language descriptions of 706 music recordings, all publicly accessible and released under Creative Common licenses. To showcase the use of our dataset, we benchmark popular models on three key music-and-language tasks (music captioning, text-to-music generation and music-language retrieval). Our experiments highlight the importance of cross-dataset evaluation and offer insights into how researchers can use SDD to gain a broader understanding of model performance., Comment: Accepted to NeurIPS 2023 Workshop on Machine Learning for Audio

Addressing the reproducibility crisis in artificial intelligence through the validation of reported experimental results is a challenging task. It necessitates either the reimplementation of techniques or a meticulous assessment of papers for deviations from the scientific method and best statistical practices. To facilitate the validation of reported results, we have developed numerical techniques capable of identifying inconsistencies between reported performance scores and various experimental setups in machine learning problems, including binary/multiclass classification and regression. These consistency tests are integrated into the open-source package mlscorecheck, which also provides specific test bundles designed to detect systematically recurring flaws in various fields, such as retina image processing and synthetic minority oversampling.

In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipulating the diffusion process. However, when separating audio sources of the same type, such as duet singing voices, the prior learned by the diffusion process may not be sufficient to maintain the consistency of the source identity in the separated audio. For example, the singer may change from one to another occasionally. Tackling this problem will be useful for separating sources in a choir, or a mixture of multiple instruments with similar timbre, without acquiring large amounts of paired data. In this paper, we examine this problem in the context of duet singing voices separation, and propose a method to enforce the coherency of singer identity by splitting the mixture into overlapping segments and performing posterior sampling in an auto-regressive manner, conditioning on the previous segment. We evaluate the proposed method on the MedleyVox dataset and show that the proposed method outperforms the naive posterior sampling baseline. Our source code and the pre-trained model are publicly available at https://github.com/iamycy/duet-svs-diffusion., Comment: 9 pages, 1 figure. Published at Sound Demixing Workshop 2023

Emerging Denoising Diffusion Probabilistic Models (DDPM) have become increasingly utilised because of promising results they have achieved in diverse generative tasks with continuous data, such as image and sound synthesis. Nonetheless, the success of diffusion models has not been fully extended to discrete symbolic music. We propose to combine a vector quantized variational autoencoder (VQ-VAE) and discrete diffusion models for the generation of symbolic music with desired composer styles. The trained VQ-VAE can represent symbolic music as a sequence of indexes that correspond to specific entries in a learned codebook. Subsequently, a discrete diffusion model is used to model the VQ-VAE's discrete latent space. The diffusion model is trained to generate intermediate music sequences consisting of codebook indexes, which are then decoded to symbolic music using the VQ-VAE's decoder. The evaluation results demonstrate our model can generate symbolic music with target composer styles that meet the given conditions with a high accuracy of 72.36%. Our code is available at https://github.com/jinchengzhanggg/VQVAE-Diffusion.

Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate discrete symbolic music because this new class of generative models are not well suited for discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model combined with a Generative Adversarial Network, aiming to (i) alleviate one of the remaining challenges in algorithmic music generation which is the control of generation towards a target emotion, and (ii) mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We first used a trained Variational Autoencoder to obtain embeddings of a symbolic music dataset with emotion labels and then used those to train a diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model achieves several orders of magnitude improvement in computational cost, requiring merely four time steps to denoise while the steps required by current state-of-the-art diffusion models for symbolic music generation is in the order of thousands.

Binary classification is a fundamental task in machine learning, with applications spanning various scientific domains. Whether scientists are conducting fundamental research or refining practical applications, they typically assess and rank classification techniques based on performance metrics such as accuracy, sensitivity, and specificity. However, reported performance scores may not always serve as a reliable basis for research ranking. This can be attributed to undisclosed or unconventional practices related to cross-validation, typographical errors, and other factors. In a given experimental setup, with a specific number of positive and negative test items, most performance scores can assume specific, interrelated values. In this paper, we introduce numerical techniques to assess the consistency of reported performance scores and the assumed experimental setup. Importantly, the proposed approach does not rely on statistical inference but uses numerical methods to identify inconsistencies with certainty. Through three different applications related to medicine, we demonstrate how the proposed techniques can effectively detect inconsistencies, thereby safeguarding the integrity of research fields. To benefit the scientific community, we have made the consistency tests available in an open-source Python package.

This paper presents a comprehensive study of automatic performer identification in expressive piano performances using convolutional neural networks (CNNs) and expressive features. Our work addresses the challenging multi-class classification task of identifying virtuoso pianists, which has substantial implications for building dynamic musical instruments with intelligence and smart musical systems. Incorporating recent advancements, we leveraged large-scale expressive piano performance datasets and deep learning techniques. We refined the scores by expanding repetitions and ornaments for more accurate feature extraction. We demonstrated the capability of one-dimensional CNNs for identifying pianists based on expressive features and analyzed the impact of the input sequence lengths and different features. The proposed model outperforms the baseline, achieving 85.3% accuracy in a 6-way identification task. Our refined dataset proved more apt for training a robust pianist identifier, making a substantial contribution to the field of automatic performer identification. Our codes have been released at https://github.com/BetsyTang/PID-CNN., Comment: 6 pages, 3 figures, accepted by the 4th International Symposium on the Internet of Sounds, IS2 2023

Effective music mixing requires technical and creative finesse, but clear communication with the client is crucial. The mixing engineer must grasp the client's expectations, and preferences, and collaborate to achieve the desired sound. The tacit agreement for the desired sound of the mix is often established using guides like reference songs and demo mixes exchanged between the artist and the engineer and sometimes verbalised using semantic terms. This paper presents the findings of a two-phased exploratory study aimed at understanding how professional mixing engineers interact with clients and use their feedback to guide the mixing process. For phase one, semi-structured interviews were conducted with five mixing engineers with the aim of gathering insights about their communication strategies, creative processes, and decision-making criteria. Based on the inferences from these interviews, an online questionnaire was designed and administered to a larger group of 22 mixing engineers during the second phase. The results of this study shed light on the importance of collaboration, empathy, and intention in the mixing process, and can inform the development of smart multi-track mixing systems that better support these practices. By highlighting the significance of these findings, this paper contributes to the growing body of research on the collaborative nature of music production and provides actionable recommendations for the design and implementation of innovative mixing tools.

We study 1-tag systems with states obeying the freezing property that only allows constant bounded number of rewrites of symbols. We look at examples of languages accepted by such systems, the accepting power of the model, as well as certain closure properties and decision problems. Finally we discuss a restriction of the system where the working alphabet must match the input alphabet., Comment: In Proceedings AFL 2023, arXiv:2309.01126

Although the design and application of audio effects is well understood, the inverse problem of removing these effects is significantly more challenging and far less studied. Recently, deep learning has been applied to audio effect removal; however, existing approaches have focused on narrow formulations considering only one effect or source type at a time. In realistic scenarios, multiple effects are applied with varying source content. This motivates a more general task, which we refer to as general purpose audio effect removal. We developed a dataset for this task using five audio effects across four different sources and used it to train and evaluate a set of existing architectures. We found that no single model performed optimally on all effect types and sources. To address this, we introduced RemFX, an approach designed to mirror the compositionality of applied effects. We first trained a set of the best-performing effect-specific removal models and then leveraged an audio effect classification model to dynamically construct a graph of our models at inference. We found our approach to outperform single model baselines, although examples with many effects present remain challenging., Comment: Preprint. Accepted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023

The term "differentiable digital signal processing" describes a family of techniques in which loss function gradients are backpropagated through digital signal processors, facilitating their integration into neural networks. This article surveys the literature on differentiable audio signal processing, focusing on its use in music & speech synthesis. We catalogue applications to tasks including music performance rendering, sound matching, and voice transformation, discussing the motivations for and implications of the use of this methodology. This is accompanied by an overview of digital signal processing operations that have been implemented differentiably. Finally, we highlight open challenges, including optimisation pathologies, robustness to real-world conditions, and design trade-offs, and discuss directions for future research., Comment: Under review for Frontiers in Signal Processing

The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface. While SAM has already been extensively evaluated in various domains, its adaptation to retinal OCT scans remains unexplored. To bridge this research gap, we conduct a comprehensive evaluation of SAM and its adaptations on a large-scale public dataset of OCTs from RETOUCH challenge. Our evaluation covers diverse retinal diseases, fluid compartments, and device vendors, comparing SAM against state-of-the-art retinal fluid segmentation methods. Through our analysis, we showcase adapted SAM's efficacy as a powerful segmentation model in retinal OCT scans, although still lagging behind established methods in some circumstances. The findings highlight SAM's adaptability and robustness, showcasing its utility as a valuable tool in retinal OCT image analysis and paving the way for further advancements in this domain.

We study the sweep complexity of DFA in one-way jumping mode answering several questions posed earlier. This measure is the number of times in the worst case that such machines have to return to the beginning of their input after having skipped some of the symbols. The class of languages accepted by these machines strictly includes the regular class and constant sweep complexity allows exactly the acceptance of regular languages. However, we show that there exist machines with higher than constant complexity still only accepting regular languages and that in general the sweep complexity of an automaton does not distinguish between accepting regular and non-regular languages. We establish separation results for asymptotic classes defined by this complexity measure and give a surprising exponential/logarithmic relation between factors of certain inputs which can be verified by such machines., Comment: 12 pages, 8 figures

Jazz pianists often uniquely interpret jazz standards. Passages from these interpretations can be viewed as sections of variation. We manually extracted such variations from solo jazz piano performances. The JAZZVAR dataset is a collection of 502 pairs of Variation and Original MIDI segments. Each Variation in the dataset is accompanied by a corresponding Original segment containing the melody and chords from the original jazz standard. Our approach differs from many existing jazz datasets in the music information retrieval (MIR) community, which often focus on improvisation sections within jazz performances. In this paper, we outline the curation process for obtaining and sorting the repertoire, the pipeline for creating the Original and Variation pairs, and our analysis of the dataset. We also introduce a new generative music task, Music Overpainting, and present a baseline Transformer model trained on the JAZZVAR dataset for this task. Other potential applications of our dataset include expressive performance analysis and performer identification., Comment: Pre-print accepted for publication at CMMR2023, 12 pages, 4 figures

This paper introduces GlOttal-flow LPC Filter (GOLF), a novel method for singing voice synthesis (SVS) that exploits the physical characteristics of the human voice using differentiable digital signal processing. GOLF employs a glottal model as the harmonic source and IIR filters to simulate the vocal tract, resulting in an interpretable and efficient approach. We show it is competitive with state-of-the-art singing voice vocoders, requiring fewer synthesis parameters and less memory to train, and runs an order of magnitude faster for inference. Additionally, we demonstrate that GOLF can model the phase components of the human voice, which has immense potential for rendering and analysing singing voices in a differentiable manner. Our results highlight the effectiveness of incorporating the physical properties of the human voice mechanism into SVS and underscore the advantages of signal-processing-based approaches, which offer greater interpretability and efficiency in synthesis., Comment: 9 pages, 4 figures. Published at ISMIR 2023

Capturing intricate and subtle variations in human expressiveness in music performance using computational approaches is challenging. In this paper, we propose a novel approach for reconstructing human expressiveness in piano performance with a multi-layer bi-directional Transformer encoder. To address the needs for large amounts of accurately captured and score-aligned performance data in training neural networks, we use transcribed scores obtained from an existing transcription model to train our model. We integrate pianist identities to control the sampling process and explore the ability of our system to model variations in expressiveness for different pianists. The system is evaluated through statistical analysis of generated expressive performances and a listening test. Overall, the results suggest that our method achieves state-of-the-art in generating human-like piano performances from transcribed scores, while fully and consistently reconstructing human expressiveness poses further challenges., Comment: 12 pages, 5 figures, accepted by CMMR2023, the 16th International Symposium on Computer Music Multidisciplinary Research

We study the length of $T$-contaminated runs of heads in the well-known coin tossing experiment. A $T$-contaminated run of heads is a sequence of consecutive heads interrupted by $T$ tails. For $T=1$ and $T=2$ we find the asymptotic distribution for the first hitting time of the $T$ contaminated run of heads having length $m$; furthermore, we obtain a limit theorem for the length of the longest $T$-contaminated head run. We prove that the rate of the approximation of our accompanying distribution for the length of the longest $T$-contaminated head run is considerably better than the previous ones. For the proof we use a powerful lemma by Cs\'aki, F\"oldes and Koml\'os., Comment: 20 pages, 4 figures