Music Generation

This paper introduces Conchordal, a bio-acoustic instrument for generative composition whose sonic agents are governed by artificial life dynamics within a psychoacoustic fitness landscape. The system is built on Direct Cognitive Coupling (DCC), a design principle requiring that generative dynamics operate directly within a landscape derived from psychoacoustic observables and read from that landscape without symbolic harmonic rules. The environment integrates roughness and harmonicity into a continuous consonance field without presupposing discrete scales or explicit harmonic rules. Agents adjust pitch through local proposal-and-accept dynamics under a crowding penalty, regulate survival via consonance-dependent metabolism, and entrain temporally through Kuramoto-style phase coupling. Four experiments are reported: (1) consonance search produces structured polyphony with enriched consonant intervals; (2) consonance-dependent metabolism yields survival differentials that vanish when recharge is disabled; (3) a minimal hereditary adaptation assay shows that parent-guided respawn plus metabolic selection can accumulate more structured polyphony without adult hill-climbing; and (4) a shared oscillatory scaffold organizes rhythmic timing under external forcing. A supplementary mechanism check reports one possible composer-configurable bridge by which spectral state can modulate temporal coupling. These findings show that a psychoacoustically derived landscape serves as an effective artificial-life terrain, yielding self-organization, selection, synchronization, and lineage-level accumulation in a non-traditional computational medium. At the level of the model, the same landscape therefore functions both as ecological terrain and as an internal proxy for musical coherence.

Composing coherent long-form music remains a significant challenge due to the complexity of modeling long-range dependencies and the prohibitive memory and computational requirements associated with lengthy audio representations. In this work, we propose a simple yet powerful trick: we assume that AI models can understand and generate time-accelerated (speeded-up) audio at rates such as 2x, 4x, or even 8x. By first generating a high-speed version of the music, we greatly reduce the temporal length and resource requirements, making it feasible to handle long-form music that would otherwise exceed memory or computational limits. The generated audio is then restored to its original speed, recovering the full temporal structure. This temporal speed-up and slow-down strategy naturally follows the principle of hierarchical generation from abstract to detailed content, and can be conveniently applied to existing music generation models to enable long-form music generation. We instantiate this idea in SqueezeComposer, a framework that employs diffusion models for generation in the accelerated domain and refinement in the restored domain. We validate the effectiveness of this approach on two tasks: long-form music generation, which evaluates temporal-wise control (including continuation, completion, and generation from scratch), and whole-song singing accompaniment generation, which evaluates track-wise control. Experimental results demonstrate that our simple temporal speed-up trick enables efficient, scalable, and high-quality long-form music generation. Audio samples are available at https://SqueezeComposer.github.io/.

Recent text-to-audio models enable adaptive game soundtracks, but small prompt changes can cause abrupt musical shifts. We evaluate MusicGen-small, MusicGen-large, and Stable Audio 2.5 under Minimal Lexical Substitution, Intensity Shifts, and Structural Rephrasing using log-Mel distance, MFCC/chroma-DTW, and CLAP similarity. Stable Audio 2.5 achieves the lowest pooled acoustic distances and the highest audio-audio CLAP similarity under structural rephrasing, while MusicGen-large has the highest audio-audio CLAP similarity under lexical substitutions and intensity shifts. Stable Audio 2.5 also shows the greatest between-seed variation in prompt-to-audio alignment, demonstrating the importance of multi-seed robustness evaluation for adaptive game audio.

In automatic music generation, a central challenge is to design controls that enable meaningful human-machine interaction. Existing systems often rely on extrinsic inputs such as text prompts or metadata, which do not allow humans to directly shape the composition. While prior work has explored intrinsic controls such as chords or hierarchical structure, these approaches mainly address piano or vocal-accompaniment settings, leaving multitrack symbolic music largely underexplored. We identify instrumentation, the choice of instruments and their roles, as a natural dimension of control in multi-track composition, and propose ViTex, a visual representation of instrumental texture. In ViTex, color encodes instrument choice, spatial position represents pitch and time, and stroke properties capture local textures. Building on this representation, we develop a discrete diffusion model conditioned on ViTex and chord progressions to generate 8-measure multi-track symbolic music, enabling explicit texture-level control while maintaining strong unconditional generation quality. The demo page and code are avaliable at https://vitex2025.github.io/.

Multi-track music generation has garnered significant research interest due to its precise mixing and remixing capabilities. However, existing models often overlook essential attributes such as rhythmic stability and synchronization, leading to a focus on differences between tracks rather than their inherent properties. In this paper, we introduce SyncTrack, a synchronous multi-track waveform music generation model designed to capture the unique characteristics of multi-track music. SyncTrack features a novel architecture that includes track-shared modules to establish a common rhythm across all tracks and track-specific modules to accommodate diverse timbres and pitch ranges. Each track-shared module employs two cross-track attention mechanisms to synchronize rhythmic information, while each track-specific module utilizes learnable instrument priors to better represent timbre and other unique features. Additionally, we enhance the evaluation of multi-track music quality by introducing rhythmic consistency through three novel metrics: Inner-track Rhythmic Stability (IRS), Cross-track Beat Synchronization (CBS), and Cross-track Beat Dispersion (CBD). Experiments demonstrate that SyncTrack significantly improves the multi-track music quality by enhancing rhythmic consistency.

A player piano can strike more keys, across more of the register, and faster than any pianist can reach. Three traditions dominate composition in that region, namely Nancarrow's tempo canons, Xenakis' stochastic distributions, and L-system grammars. They have developed in isolation, and none of them accounts for the instrument itself. A Disklavier does not answer instantly, because a loud note reaches the string sooner than a soft one, so music written as if the mechanism were transparent arrives distorted. We present Amanous, a hardware-aware composition system for the Yamaha Disklavier that unifies the three traditions through distribution-switching, in which each grammar symbol selects an entire distributional regime rather than adjusting parameters within a fixed one. A four-layer pipeline carries a symbol from grammar to actuation-ready MIDI. An L-system fixes the macro-form, each symbol is mapped to distributions and a tempo-canon ratio, events are sampled and time-scaled, and a hardware layer pre-compensates velocity-dependent latency and enforces the key-reset time. Convergence points close a feedback loop, letting the music's own temporal structure trigger the next switch. Sections from different symbols remain statistically separable at the output, and ablating the L-system, the tempo canon, or the hardware compensation each degrades a distinct property. Under the modelled latency curve, pre-compensation takes the mean onset error from roughly 18 ms to below the instrument's 1 ms scanning resolution. Structured and random textures are most separable near 25 notes/s, and melodic metrics lose their discriminative power over the 40-100 notes/s band, above which the difference is consistent with distributional content rather than melodic order. All results are computational, nothing was played or measured on an instrument, and a psychoacoustic protocol is proposed for future work.

Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it challenging to produce ancient music with distinct rhythms and styles, such as ancient Chinese SongCi. In this paper, we introduce SongSong, the first music generation model capable of restoring Chinese SongCi to our knowledge. Our model first predicts the melody from the input SongCi, then separately generates the singing voice and accompaniment based on that melody, and finally combines all elements to create the final piece of music. Additionally, to address the lack of ancient music datasets, we create OpenSongSong, a comprehensive dataset of ancient Chinese SongCi music, featuring 29.9 hours of compositions by various renowned SongCi music masters. To assess SongSong's proficiency in performing SongCi, we randomly select 85 SongCi sentences that were not part of the training set for evaluation against SongSong and music generation platforms such as Suno and SkyMusic. The subjective and objective outcomes indicate that our proposed model achieves leading performance in generating high-quality SongCi music.

While end-to-end lyrics-to-song models offer convenience for casual users, professional songwriters require score-to-song systems that allow them to retain authorship over the core melody. However, existing score-to-song methods are limited to short-form snippets and fail to maintain coherence in long-form generation, particularly during vocal-silent sections like intros and bridges. To address this long-form bottleneck, we propose MIDI-informed singing accompaniment generation (MIDI-SAG). Unlike conventional audio-only models, MIDI-SAG utilizes symbolic timing and chord information derived from the vocal MIDI to provide a stable musical roadmap. By incorporating structure planning, which defines temporal boundaries and semantic labels, our framework facilitates consistent generation across both vocal and non-vocal sections. We demonstrate the feasibility of this compositional pipeline by leveraging specialized pre-trained modules, enabling data-efficient training on a single GPU. Our experiments show the potential of this approach for both professional score-to-song and general lyrics-to-song tasks. While an early exploration, MIDI-SAG suggests a promising direction for structured, long-form music synthesis. Audio demos are available, and the code will be open-sourced at https://composerflow.github.io/web_revealed/.

Cover songs constitute a vital aspect of musical culture, preserving the core melody of an original composition while reinterpreting it to infuse novel emotional depth and thematic emphasis. Although prior research has explored the reinterpretation of instrumental music through melody-conditioned text-to-music models, the task of cover song generation remains largely unaddressed. In this work, we reformulate our cover song generation as a conditional generation, which simultaneously generates new vocals and accompaniment conditioned on the original vocal melody and text prompts. To this end, we present SongEcho, which leverages Instance-Adaptive Element-wise Linear Modulation (IA-EiLM), a framework that incorporates controllable generation by improving both conditioning injection mechanism and conditional representation. To enhance the conditioning injection mechanism, we extend Feature-wise Linear Modulation (FiLM) to an Element-wise Linear Modulation (EiLM), to facilitate precise temporal alignment in melody control. For conditional representations, we propose Instance-Adaptive Condition Refinement (IACR), which refines conditioning features by interacting with the hidden states of the generative model, yielding instance-adaptive conditioning. Additionally, to address the scarcity of large-scale, open-source full-song datasets, we construct Suno70k, a high-quality AI song dataset enriched with comprehensive annotations. Experimental results across multiple datasets demonstrate that our approach generates superior cover songs compared to existing methods, while requiring fewer than 30% of the trainable parameters. The code, dataset, and demos are available at https://github.com/lsfhuihuiff/SongEcho_ICLR2026.

For computational efficiency, modern language models are typically trained on independently sampled fixed-length sequences. Symbolic music language models largely inherit this paradigm, despite musical structure naturally unfolding over complete compositions rather than isolated excerpts. Fragmenting compositions into independent training instances therefore prevents continuous conditioning over the complete work. We present a practical framework for whole-piece training of symbolic music language models via Full-Horizon Compressed Recurrence (FHCR). FHCR preserves the full temporal horizon of recurrent memory while reducing the dimensionality of its key-value (KV) representation, making continuous whole-piece training practical under limited GPU memory. To directly assess functional long-range dependence, we introduce KV-Reset Context Utilization (KRCU), an evaluation-time diagnostic. On the MAESTRO symbolic piano dataset, KRCU shows that full-horizon models utilize context far beyond the local segment window, whereas reducing the temporal extent of recurrent memory substantially weakens this measurable long-range dependence. FHCR preserves long-range context utilization while substantially reducing recurrent memory cost. These findings show that preserving the temporal extent of recurrent history is important for efficient whole-piece modeling, and that memory cost can instead be reduced through KV representation compression. The project demos and generated music samples are available at https://wholemusic.github.io.

Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from images. However, existing image-conditioned systems suffer from two fundamental limitations: (i) they are typically trained on natural photographs, limiting their ability to capture the richer semantic, stylistic, and cultural content of artworks; and (ii) most rely on an image-to-text conversion stage, using language as a semantic shortcut that simplifies conditioning but prevents direct visual-to-audio learning. Motivated by these gaps, we introduce ArtSound, a large-scale multimodal dataset of 105,884 artwork-music pairs enriched with dual-modality captions, obtained by extending ArtGraph and the Free Music Archive. We further propose ArtToMus, the first framework explicitly designed for direct artwork-to-music generation, which maps digitized artworks to music without image-to-text translation or language-based semantic supervision. The framework projects visual embeddings into the conditioning space of a latent diffusion model, enabling music synthesis guided solely by visual information. Experimental results show that ArtToMus generates musically coherent and stylistically consistent outputs that reflect salient visual cues of the source artworks. While absolute alignment scores remain lower than those of text-conditioned systems-as expected given the substantially increased difficulty of removing linguistic supervision-ArtToMus achieves competitive perceptual quality and meaningful cross-modal correspondence. This work establishes direct visual-to-music generation as a distinct and challenging research direction, and provides resources that support applications in multimedia art, cultural heritage, and AI-assisted creative practice. Code and dataset will be publicly released upon acceptance.

We introduce a structure-aware approach for symbolic piano accompaniment that decouples high-level planning from note-level realization. A lightweight transformer predicts an interpretable, per-measure style plan conditioned on section/phrase structure and functional harmony, and a retriever then selects and reharmonizes human-performed piano patterns from a corpus. We formulate retrieval as pattern matching under an explicit energy with terms for harmonic feasibility, structural-role compatibility, voice-leading continuity, style preferences, and repetition control. Given a structured lead sheet and optional keyword prompts, the system generates piano-accompaniment MIDI. In our experiments, transformer style-planner-guided retrieval produces diverse long-form accompaniments with strong style realization. We further analyze planner ablations and quantify inter-style isolation. Experimental results demonstrate the effectiveness of our inference-time approach for piano accompaniment generation.

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio stream (e.g., a singer singing), it has to also simultaneously generate in real-time a coherent accompanying stream (e.g., a guitar accompaniment). In this work, we propose a model design considering inevitable system delays in practical deployment with two design variables: future visibility $t_f$, the offset between the output playback time and the latest input time used for conditioning, and output chunk duration $k$, the number of frames emitted per call. We train Transformer decoders across a grid of $(t_f,k)$ and show two consistent trade-offs: increasing effective $t_f$ improves coherence by reducing the recency gap, but requires faster inference to stay within the latency budget; increasing $k$ improves throughput but results in degraded accompaniment due to a reduced update rate. Finally, we observe that naive maximum-likelihood streaming training is insufficient for coherent accompaniment where future context is not available, motivating advanced anticipatory and agentic objectives for live jamming.

We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no open-source high-quality dataset representing popular and well-known songs for generative music modeling tasks such as text-music, music-captioning, singing-voice synthesis, melody reconstruction and cross-model retrieval. Past contributions focused on isolated and constrained factors whose core perspective was to create synthetic or re-recorded music corpus (e.g. GTSinger, M4Singer) and arbitrarily large-scale audio datasets (e.g. DISCO-10M and LAIONDISCO-12M) had been another focus for the community. Unfortunately, adoption of these datasets has been below substantial in the generative music community as these datasets fail to reflect real-world music and its flavour. Our dataset changes this narrative and provides a dataset that is constructed using actual popular music and world-renowned artists.

The ultimate purpose of generative music AI is music production. The studio-lab, a social form within the art-science branch of cross-disciplinarity, is a way to advance music production with AI music models. During a studio-lab experiment involving researchers, music producers, and an AI model for music generating bass-like audio, it was observed that the producers used the model's output to convey two or more pitches with a single harmonic complex tone, which in turn revealed that the model had learned to generate structured and coherent simultaneous melodic lines using monophonic sequences of harmonic complex tones. These findings prompt a reconsideration of the long-standing debate on whether humans can perceive harmonics as distinct pitches and highlight how generative AI can not only enhance musical creativity but also contribute to a deeper understanding of music.

There have been several studies on automatically generating piano covers, and recent advancements in deep learning have enabled the creation of more sophisticated covers. However, existing automatic piano cover models still have room for improvement in terms of expressiveness and fidelity to the original. To address these issues, we propose a learning algorithm called AMT-APC, which leverages the capabilities of automatic music transcription models. By utilizing the strengths of well-established automatic music transcription models, we aim to improve the accuracy of piano cover generation. Our experiments demonstrate that the AMT-APC model reproduces original tracks more accurately than any existing models.

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 symbolic music since this class of generative models struggles with discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model integrated with a Generative Adversarial Network, aiming to mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We enable the use of diffusion model by representing symbolic music as image-like pianorolls with velocity values instead of discrete event tokens and then used a Variational Autoencoder to obtain their latent representations to train the proposed diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model uses merely 15 denoising diffusion steps to produce high-quality music, while most diffusion models for symbolic music generation require hundreds or thousands of steps.