Singing is one of the most cherished forms of human entertainment. However, creating a beautiful song requires an accompaniment that complements the vocals and aligns well with the song instruments and genre. With advancements in deep learning, previous research has focused on generating suitable accompaniments but often lacks precise alignment with the desired instrumentation and genre. To address this, we propose a straightforward method that enables control over the accompaniment through text prompts, allowing the generation of music that complements the vocals and aligns with the song instrumental and genre requirements. Through extensive experiments, we successfully generate 10-second accompaniments using vocal input and text control.

Text-to-song (TTSong) is a music generation task that synthesizes accompanied singing voices. Current TTSong methods, inherited from singing voice synthesis (SVS), require melody-related information that can sometimes be impractical, such as music scores or MIDI sequences. We present MelodyLM, the first TTSong model that generates high-quality song pieces with fully text-controlled melodies, achieving minimal user requirements and maximum control flexibility. MelodyLM explicitly models MIDI as the intermediate melody-related feature and sequentially generates vocal tracks in a language model manner, conditioned on textual and vocal prompts. The accompaniment music is subsequently synthesized by a latent diffusion model with hybrid conditioning for temporal alignment. With minimal requirements, users only need to input lyrics and a reference voice to synthesize a song sample. For full control, just input textual prompts or even directly input MIDI. Experimental results indicate that MelodyLM achieves superior performance in terms of both objective and subjective metrics. Audio samples are available at https://melodylm666.github.io.

Singing Accompaniment Generation (SAG), which generates instrumental music to accompany input vocals, is crucial to developing human-AI symbiotic art creation systems. The state-of-the-art method, SingSong, utilizes a multi-stage autoregressive (AR) model for SAG, however, this method is extremely slow as it generates semantic and acoustic tokens recursively, and this makes it impossible for real-time applications. In this paper, we aim to develop a Fast SAG method that can create high-quality and coherent accompaniments. A non-AR diffusion-based framework is developed, which by carefully designing the conditions inferred from the vocal signals, generates the Mel spectrogram of the target accompaniment directly. With diffusion and Mel spectrogram modeling, the proposed method significantly simplifies the AR token-based SingSong framework, and largely accelerates the generation. We also design semantic projection, prior projection blocks as well as a set of loss functions, to ensure the generated accompaniment has semantic and rhythm coherence with the vocal signal. By intensive experimental studies, we demonstrate that the proposed method can generate better samples than SingSong, and accelerate the generation by at least 30 times. Audio samples and code are available at https://fastsag.github.io/.

We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of stems (or their combinations) composing music tracks and allows the objective evaluation of compositional models for music in the task of accompaniment generation. We also introduce a new baseline for compositional music generation called CompoNet, based on ControlNet, generalizing the tasks of MSDM, and quantify it against the latter using COCOLA. We release all models trained on public datasets containing separate stems (MUSDB18-HQ, MoisesDB, Slakh2100, and CocoChorales).

Music generated by deep learning methods often suffers from a lack of coherence and long-term organization. Yet, multi-scale hierarchical structure is a distinctive feature of music signals. To leverage this information, we propose a structure-informed positional encoding framework for music generation with Transformers. We design three variants in terms of absolute, relative and non-stationary positional information. We comprehensively test them on two symbolic music generation tasks: next-timestep prediction and accompaniment generation. As a comparison, we choose multiple baselines from the literature and demonstrate the merits of our methods using several musically-motivated evaluation metrics. In particular, our methods improve the melodic and structural consistency of the generated pieces.

ABSTRACT We propose Polyffusion, a diffusion model that generates polyphonic music scores by regarding music as imagelike piano roll representations. The model is capable of controllable music generation with two paradigms: internal control and external control. We show that by using tive modeling [14,15], symbolic music generation still suffers internal and external controls, Polyffusion unifies a from the lack of controllability and consistency at different wide range of music creation tasks, including melody generation time scales [16]. In our study, we experiment with given accompaniment, accompaniment generation the idea of using diffusion models to approach controllable given melody, arbitrary music segment inpainting, and music symbolic music generation. Experimental results Inspired by the high-quality and controllable image show that our model significantly outperforms existing generation that diffusion models have achieved in computer Transformer and sampling-based baselines, and using vision, we devise an image-like piano roll format as pre-trained disentangled representations as external conditions the input, and used a UNet-based diffusion model to stepwise yields more effective controls.