Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio

Music exists in various modalities, such as score images, symbolic scores, MIDI, and audio. Translations between each modality are established as core tasks of music information retrieval, such as automatic music transcription (audio-to-MIDI) and optical music recognition (score image to symbolic score). However, most past work on multimodal translation trains specialized models on individual translation tasks. In this paper, we propose a unified approach, where we train a general-purpose model on many translation tasks simultaneously. Two key factors make this unified approach viable: a new large-scale dataset and the tokenization of each modality. Firstly, we propose a new dataset that consists of more than 1,300 hours of paired audio-score image data collected from YouTube videos, which is an order of magnitude larger than any existing music modal translation datasets. Secondly, our unified tokenization framework discretizes score images, audio, MIDI, and MusicXML into a sequence of tokens, enabling a single encoder-decoder Transformer to tackle multiple cross-modal translation as one coherent sequence-to-sequence task. Experimental results confirm that our unified multitask model improves upon single-task baselines in several key areas, notably reducing the symbol error rate for optical music recognition from 24.58% to a state-of-the-art 13.67%, while similarly substantial improvements are observed across the other translation tasks. Notably, our approach achieves the first successful score-image-conditioned audio generation, marking a significant breakthrough in cross-modal music generation.

Extending Visual Dynamics for Video-to-Music Generation

Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios or undervalue the visual dynamics. To address these limitations, we focus on tackling the complexity of dynamics and resolving temporal misalignment between video and music representations. To this end, we propose DyViM, a novel framework to enhance dynamics modeling for video-to-music generation. Specifically, we extract frame-wise dynamics features via a simplified motion encoder inherited from optical flow methods, followed by a self-attention module for aggregation within frames. These dynamic features are then incorporated to extend existing music tokens for temporal alignment. Additionally, high-level semantics are conveyed through a cross-attention mechanism, and an annealing tuning strategy benefits to fine-tune well-trained music decoders efficiently, therefore facilitating seamless adaptation. Extensive experiments demonstrate DyViM's superiority over state-of-the-art (SOTA) methods.

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning. Recent LALMs typically augment Large Language Models (LLMs) with auditory capabilities by training on large-scale, manually curated or LLM-synthesized audio-instruction datasets. However, these approaches have often suffered from the catastrophic forgetting of the LLM's original language abilities. To address this, we revisit the data construction pipeline and propose DeSTA, a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets. This approach preserves the LLM's native language proficiency while establishing effective audio-text alignment, thereby enabling zero-shot generalization without task-specific tuning. Using DeSTA, we construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms widely adopted data construction and training strategies in both auditory perception and instruction-following capabilities. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs.

GlobalMood: A cross-cultural benchmark for music emotion recognition

Human annotations of mood in music are essential for music generation and recommender systems. However, existing datasets predominantly focus on Western songs with mood terms derived from English, which may limit generalizability across diverse linguistic and cultural backgrounds. To address this, we introduce `GlobalMood', a novel cross-cultural benchmark dataset comprising 1,180 songs sampled from 59 countries, with large-scale annotations collected from 2,519 individuals across five culturally and linguistically distinct locations: U.S., France, Mexico, S. Korea, and Egypt. Rather than imposing predefined mood categories, we implement a bottom-up, participant-driven approach to organically elicit culturally specific music-related mood terms. We then recruit another pool of human participants to collect 988,925 ratings for these culture-specific descriptors. Our analysis confirms the presence of a valence-arousal structure shared across cultures, yet also reveals significant divergences in how certain mood terms, despite being dictionary equivalents, are perceived cross-culturally. State-of-the-art multimodal models benefit substantially from fine-tuning on our cross-culturally balanced dataset, as evidenced by improved alignment with human evaluations - particularly in non-English contexts. More broadly, our findings inform the ongoing debate on the universality versus cultural specificity of emotional descriptors, and our methodology can contribute to other multimodal and cross-lingual research.

DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis

In recent years, generative adversarial networks (GANs) have made significant progress in generating audio sequences. However, these models typically rely on bandwidth-limited mel-spectrograms, which constrain the resolution of generated audio sequences, and lead to mode collapse during conditional generation. To address this issue, we propose Deformable Periodic Network based GAN (DPN-GAN), a novel GAN architecture that incorporates a kernel-based periodic ReLU activation function to induce periodic bias in audio generation. This innovative approach enhances the model's ability to capture and reproduce intricate audio patterns. In particular, our proposed model features a DPN module for multi-resolution generation utilizing deformable convolution operations, allowing for adaptive receptive fields that improve the quality and fidelity of the synthetic audio. Additionally, we enhance the discriminator network using deformable convolution to better distinguish between real and generated samples, further refining the audio quality. We trained two versions of the model: DPN-GAN small (38.67M parameters) and DPN-GAN large (124M parameters). For evaluation, we use five different datasets, covering both speech synthesis and music generation tasks, to demonstrate the efficiency of the DPN-GAN. The experimental results demonstrate that DPN-GAN delivers superior performance on both out-of-distribution and noisy data, showcasing its robustness and adaptability. Trained across various datasets, DPN-GAN outperforms state-of-the-art GAN architectures on standard evaluation metrics, and exhibits increased robustness in synthesized audio.

Audio-Sync Video Generation with Multi-Stream Temporal Control

Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video generation. MTV explicitly separates audios into speech, effects, and music tracks, enabling disentangled control over lip motion, event timing, and visual mood, respectively -- resulting in fine-grained and semantically aligned video generation. To support the framework, we additionally present DEMIX, a dataset comprising high-quality cinematic videos and demixed audio tracks. DEMIX is structured into five overlapped subsets, enabling scalable multi-stage training for diverse generation scenarios. Extensive experiments demonstrate that MTV achieves state-of-the-art performance across six standard metrics spanning video quality, text-video consistency, and audio-video alignment. Project page: https://hjzheng.net/projects/MTV/.

Calliope: An Online Generative Music System for Symbolic Multi-Track Composition

With the rise of artificial intelligence in recent years, there has been a rapid increase in its application towards creative domains, including music. There exist many systems built that apply machine learning approaches to the problem of computer-assisted music composition (CAC). Calliope is a web application that assists users in performing a variety of multi-track composition tasks in the symbolic domain. The user can upload (Musical Instrument Digital Interface) MIDI files, visualize and edit MIDI tracks, and generate partial (via bar in-filling) or complete multi-track content using the Multi-Track Music Machine (MMM). Generation of new MIDI excerpts can be done in batch and can be combined with active playback listening for an enhanced assisted-composition workflow. The user can export generated MIDI materials or directly stream MIDI playback from the system to their favorite Digital Audio Workstation (DAW). We present a demonstration of the system, its features, generative parameters and describe the co-creative workflows that it affords.

Deep learning for music generation. Four approaches and their comparative evaluation

This paper introduces four different artificial intelligence algorithms for music generation and aims to compare these methods not only based on the aesthetic quality of the generated music but also on their suitability for specific applications. The first set of melodies is produced by a slightly modified visual transformer neural network that is used as a language model. The second set of melodies is generated by combining chat sonification with a classic transformer neural network (the same method of music generation is presented in a previous research), the third set of melodies is generated by combining the Schillinger rhythm theory together with a classic transformer neural network, and the fourth set of melodies is generated using GPT3 transformer provided by OpenAI. A comparative analysis is performed on the melodies generated by these approaches and the results indicate that significant differences can be observed between them and regarding the aesthetic value of them, GPT3 produced the most pleasing melodies, and the newly introduced Schillinger method proved to generate better sounding music than previous sonification methods.

A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives: Data, Methods, and Challenges

Multi-modal music generation, using multiple modalities like images, video, and text alongside musical scores and audio as guidance, is an emerging research area with broad applications. This paper reviews this field, categorizing music generation systems from the perspective of modalities. It covers modality representation, multi-modal data alignment, and their utilization to guide music generation. We also discuss current datasets and evaluation methods. Key challenges in this area include effective multi-modal integration, large-scale comprehensive datasets, and systematic evaluation methods. Finally, we provide an outlook on future research directions focusing on multi-modal fusion, alignment, data, and evaluation.

Do Music Preferences Reflect Cultural Values? A Cross-National Analysis Using Music Embedding and World Values Survey

This study explores the extent to which national music preferences reflect underlying cultural values. We collected long-term popular music data from YouTube Music Charts across 62 countries, encompassing both Western and non-Western regions, and extracted audio embeddings using the CLAP model. To complement these quantitative representations, we generated semantic captions for each track using LP-MusicCaps and GPT-based summarization. Countries were clustered based on contrastive embeddings that highlight deviations from global musical norms. The resulting clusters were projected into a two-dimensional space via t-SNE for visualization and evaluated against cultural zones defined by the World Values Survey (WVS). Statistical analyses, including MANOVA and chi-squared tests, confirmed that music-based clusters exhibit significant alignment with established cultural groupings. Furthermore, residual analysis revealed consistent patterns of overrepresentation, suggesting non-random associations between specific clusters and cultural zones. These findings indicate that national-level music preferences encode meaningful cultural signals and can serve as a proxy for understanding global cultural boundaries.