Low-Complexity MUSIC Algorithm: From Finite-Precision Perspective

The high computational complexity of the multiple signal classification (MUSIC) algorithm is mainly caused by the subspace decomposition and spectrum search, especially for frequent real-time applications or massive sensors. In this paper, we propose a low-complexity MUSIC algorithm from finite-precision arithmetic perspective. First, we analyze the computational bottlenecks of the classic low-complexity randomized unitary-based MUSIC (RU-MUSIC), formulating this computational issue as an inner product problem. Then, a mixed-precision method is introduced to address this problem. Specifically, this method partitions summations in inner products into blocks, where intra-block computations use low-precision arithmetic and inter-block sums use high-precision arithmetic. To further improve computational accuracy, we develop an adaptive-precision method that supports adaptive block sizes and multiple precision levels. Finally, simulation results show that the proposed finite-precision MUSIC design achieves direction-of-arrival (DOA) estimation performance similar to that using full-precision arithmetic while reducing more than 50\% computational cost.

CCMusic: An Open and Diverse Database for Chinese Music Information Retrieval Research

Data are crucial in various computer-related fields, including music information retrieval (MIR), an interdisciplinary area bridging computer science and music. This paper introduces CCMusic, an open and diverse database comprising multiple datasets specifically designed for tasks related to Chinese music, highlighting our focus on this culturally rich domain. The database integrates both published and unpublished datasets, with steps taken such as data cleaning, label refinement, and data structure unification to ensure data consistency and create ready-to-use versions. We conduct benchmark evaluations for all datasets using a unified evaluation framework developed specifically for this purpose. This publicly available framework supports both classification and detection tasks, ensuring standardized and reproducible results across all datasets. The database is hosted on HuggingFace and ModelScope, two open and multifunctional data and model hosting platforms, ensuring ease of accessibility and usability.

Lead Instrument Detection from Multitrack Music

Prior approaches to lead instrument detection primarily analyze mixture audio, limited to coarse classifications and lacking generalization ability. This paper presents a novel approach to lead instrument detection in multitrack music audio by crafting expertly annotated datasets and designing a novel framework that integrates a self-supervised learning model with a track-wise, frame-level attention-based classifier. This attention mechanism dynamically extracts and aggregates track-specific features based on their auditory importance, enabling precise detection across varied instrument types and combinations. Enhanced by track classification and permutation augmentation, our model substantially outperforms existing SVM and CRNN models, showing robustness on unseen instruments and out-of-domain testing. We believe our exploration provides valuable insights for future research on audio content analysis in multitrack music settings.

Mixed Near-field and Far-field Target Localization for Low-altitude Economy

In this paper, we study efficient mixed near-field and far-field target localization methods for low-altitude economy, by capitalizing on extremely large-scale multiple-input multiple-output (XL-MIMO) communication systems. Compared with existing works, we address three new challenges in localization, arising from 1) half-wavelength antenna spacing constraint, 2) hybrid uniform planar array (UPA) architecture, and 3) incorrect mixed-field target classification for near-field targets.To address these issues, we propose a new three-step mixed-field localization method.First, we reconstruct the signals received at UPA antennas by judiciously designing analog combining matrices over time with minimum recovery errors, thus tackling the reduced-dimensional signal-space issue in hybrid arrays.Second, based on recovered signals, we devise a modified MUSIC algorithm (catered to UPA architecture) to estimate 2D angular parameters of both far- and near-field targets. Due to half-wavelength inter-antenna spacing, there exist ambiguous angles when estimating true angles of targets.In the third step, we design an effective classification method to distinguish mixed-field targets, determine true angles of all targets, as well as estimate the ranges of near-field targets. In particular, angular ambiguity is resolved by showing an important fact that the three types of estimated angles (i.e., far-field, near-field, and ambiguous angles) exhibit significantly different patterns in the range-domain MUSIC spectrum. Furthermore, to characterize the estimation error lower-bound, we obtain a matrix closed-form Cram\'er-Rao bounds for mixed-field target localization. Finally, numerical results demonstrate the effectiveness of our proposed mixed-field localization method, which improves target-classification accuracy and achieves a lower root mean square error than various benchmark schemes.

BAN: Neuroanatomical Aligning in Auditory Recognition between Artificial Neural Network and Human Cortex

Drawing inspiration from neurosciences, artificial neural networks (ANNs) have evolved from shallow architectures to highly complex, deep structures, yielding exceptional performance in auditory recognition tasks. However, traditional ANNs often struggle to align with brain regions due to their excessive depth and lack of biologically realistic features, like recurrent connection. To address this, a brain-like auditory network (BAN) is introduced, which incorporates four neuroanatomically mapped areas and recurrent connection, guided by a novel metric called the brain-like auditory score (BAS). BAS serves as a benchmark for evaluating the similarity between BAN and human auditory recognition pathway. We further propose that specific areas in the cerebral cortex, mainly the middle and medial superior temporal (T2/T3) areas, correspond to the designed network structure, drawing parallels with the brain's auditory perception pathway. Our findings suggest that the neuroanatomical similarity in the cortex and auditory classification abilities of the ANN are well-aligned. In addition to delivering excellent performance on a music genre classification task, the BAN demonstrates a high BAS score. In conclusion, this study presents BAN as a recurrent, brain-inspired ANN, representing the first model that mirrors the cortical pathway of auditory recognition.

A Comprehensive Survey on Generative AI for Video-to-Music Generation

The burgeoning growth of video-to-music generation can be attributed to the ascendancy of multimodal generative models. However, there is a lack of literature that comprehensively combs through the work in this field. To fill this gap, this paper presents a comprehensive review of video-to-music generation using deep generative AI techniques, focusing on three key components: visual feature extraction, music generation frameworks, and conditioning mechanisms. We categorize existing approaches based on their designs for each component, clarifying the roles of different strategies. Preceding this, we provide a fine-grained classification of video and music modalities, illustrating how different categories influence the design of components within the generation pipelines. Furthermore, we summarize available multimodal datasets and evaluation metrics while highlighting ongoing challenges in the field.

Musical Heritage Historical Entity Linking

Linking named entities occurring in text to their corresponding entity in a Knowledge Base (KB) is challenging, especially when dealing with historical texts. In this work, we introduce Musical Heritage named Entities Recognition, Classification and Linking (MHERCL), a novel benchmark consisting of manually annotated sentences extrapolated from historical periodicals of the music domain. MHERCL contains named entities under-represented or absent in the most famous KBs. We experiment with several State-of-the-Art models on the Entity Linking (EL) task and show that MHERCL is a challenging dataset for all of them. We propose a novel unsupervised EL model and a method to extend supervised entity linkers by using Knowledge Graphs (KGs) to tackle the main difficulties posed by historical documents. Our experiments reveal that relying on unsupervised techniques and improving models with logical constraints based on KGs and heuristics to predict NIL entities (entities not represented in the KB of reference) results in better EL performance on historical documents.

Supervised contrastive learning from weakly-labeled audio segments for musical version matching

Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match musical versions at the track level (e.g., whole song). However, most applications require to match them at the segment level (e.g., 20s chunks). In addition, existing approaches resort to classification and triplet losses, disregarding more recent losses that could bring meaningful improvements. In this paper, we propose a method to learn from weakly annotated segments, together with a contrastive loss variant that outperforms well-studied alternatives. The former is based on pairwise segment distance reductions, while the latter modifies an existing loss following decoupling, hyper-parameter, and geometric considerations. With these two elements, we do not only achieve state-of-the-art results in the standard track-level evaluation, but we also obtain a breakthrough performance in a segment-level evaluation. We believe that, due to the generality of the challenges addressed here, the proposed methods may find utility in domains beyond audio or musical version matching.

Impact of Model Mismatch on DOA Estimation with MUSIC: Near-Field and Far-Field

There has been substantial work on developing variants of the multiple signal classification (MUSIC) algorithms that take advantage of the information present in the near-field propagation regime. However, it is not always easy to determine the correct propagation regime, which opens the possibility of incorrectly applying simpler algorithms (meant for far-field) in the near-field regime. Inspired by this, we use simulation results to investigate the performance drop when there is a mismatch between the signal model in the MUSIC algorithm and the propagation regime. For direction of arrival (DOA) estimation, we consider the cases when the receiver is in the near-field region but uses i) the near-field model, ii) the approximate near-field model (ANM) model, and iii) the far-field model to design the beamforming matrix in the MUSIC algorithm. We also consider the case when the receiver is in the far-field region, and we use the correct far-field model to design the beamforming matrix in the MUSIC algorithm. One contribution is that in the near-field, we have quantified the loss in performance when the ANM and the far-field model are used to create the beamforming matrix for the MUSIC algorithm, causing a reduction in estimation accuracy compared to the case when the correct near-field model is used to design the beamforming matrix. Another result is that in the near-field, when we incorrectly assume that the receiver is in the far-field and subsequently use the far-field beamforming matrix, we underestimate the DOA estimation error. Finally, we show that the MUSIC algorithm can provide very accurate range estimates for distances less than the Fraunhofer distance. This estimate gradually becomes inaccurate as the distances exceed the Fraunhofer distance.

Hybrid Fingerprint-based Positioning in Cell-Free Massive MIMO Systems

Recently, there has been an increasing interest in 6G technology for integrated sensing and communications, where positioning stands out as a key application. In the realm of 6G, cell-free massive multiple-input multiple-output (MIMO) systems, featuring distributed base stations equipped with a large number of antennas, present an abundant source of angle-of-arrival (AOA) information that could be exploited for positioning applications. In this paper we leverage this AOA information at the base stations using the multiple signal classification (MUSIC) algorithm, in conjunction with received signal strength (RSS) for positioning through Gaussian process regression (GPR). An AOA fingerprint database is constructed by capturing the angle data from multiple locations across the network area and is combined with RSS data from the same locations to form a hybrid fingerprint which is then used to train a GPR model employing a squared exponential kernel. The trained regression model is subsequently utilized to estimate the location of a user equipment. Simulations demonstrate that the GPR model with hybrid input achieves better positioning accuracy than traditional GPR models utilizing RSS-only and AOA-only inputs.