Audio Generation

We propose Diffusion Inference-Time T-Optimization (DITTO), a general-purpose framework for controlling pre-trained text-to-music diffusion models at inference-time via optimizing initial noise latents. Our method can be used to optimize through any differentiable feature matching loss to achieve a target (stylized) output and leverages gradient checkpointing for memory efficiency. We demonstrate a surprisingly wide-range of applications for music generation including inpainting, outpainting, and looping as well as intensity, melody, and musical structure control – all without ever fine-tuning the underlying model. When we compare our approach against related training, guidance, and optimization-based methods, we find DITTO achieves state-of-the-art performance on nearly all tasks, including outperforming comparable approaches on controllability, audio quality, and computational efficiency, thus opening the door for high-quality, flexible, training-free control of diffusion models. Sound examples can be found at https://ditto-music.github.io/web/.

Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio track. We present a novel approach, referred to as **PPAE**, which serves as a general module for diffusion models and enables precise audio editing. The editing is based on the input textual prompt only and is entirely training-free. We exploit the cross-attention maps of diffusion models to facilitate accurate local editing and employ a hierarchical local-global pipeline to ensure a smoother editing process. Experimental results highlight the effectiveness of our method in various editing tasks.

We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the conditional distribution of semantic and acoustic features. Additionally, we leverage masked prediction as the training objective, enabling the model to generalize to other tasks such as music infilling and continuation in a zero-shot manner. Experiments on MusicCaps reveal that the music generated by MusicFlow exhibits superior quality and text coherence despite being over $2\sim5$ times smaller and requiring $5$ times fewer iterative steps. Simultaneously, the model can perform other music generation tasks and achieves competitive performance in music infilling and continuation.

Despite the impressive performance of deep learning models across diverse tasks, their complexity poses challenges for interpretation. This challenge is particularly evident for audio signals, where conveying interpretations becomes inherently difficult. To address this issue, we introduce Listenable Maps for Audio Classifiers (L-MAC), a posthoc interpretation method that generates faithful and listenable interpretations. L-MAC utilizes a decoder on top of a pretrained classifier to generate binary masks that highlight relevant portions of the input audio. We train the decoder with a loss function that maximizes the confidence of the classifier decision on the masked-in portion of the audio while minimizing the probability of model output for the masked-out portion. Quantitative evaluations on both in-domain and out-of-domain data demonstrate that L-MAC consistently produces more faithful interpretations than several gradient and masking-based methodologies. Furthermore, a user study confirms that, on average, users prefer the interpretations generated by the proposed technique.

Video encompasses both visual and auditory data, creating a perceptually rich experience where these two modalities complement each other. As such, videos are a valuable type of media for the investigation of the interplay between audio and visual elements. Previous studies of audio-visual modalities primarily focused on either audio-visual representation learning or generative modeling of a modality conditioned on the other, creating a disconnect between these two branches. A unified framework that learns representation and generates modalities has not been developed yet. In this work, we introduce a novel framework called Vision to Audio and Beyond (VAB) to bridge the gap between audio-visual representation learning and vision-to-audio generation. The key approach of VAB is that rather than working with raw video frames and audio data, VAB performs representation learning and generative modeling within latent spaces. In particular, VAB uses a pre-trained audio tokenizer and an image encoder to obtain audio tokens and visual features, respectively. It then performs the pre-training task of visual-conditioned masked audio token prediction. This training strategy enables the model to engage in contextual learning and simultaneous video-to-audio generation. After the pre-training phase, VAB employs the iterative-decoding approach to rapidly generate audio tokens conditioned on visual features. Since VAB is a unified model, its backbone can be fine-tuned for various audio-visual downstream tasks. Our experiments showcase the efficiency of VAB in producing high-quality audio from video, and its capability to acquire semantic audio-visual features, leading to competitive results in audio-visual retrieval and classification.

Generating long-form 44.1kHz stereo audio from text prompts can be computationally demanding. Further, most previous works do not tackle that music and sound effects naturally vary in their duration. Our research focuses on the efficient generation of long-form, variable-length stereo music and sounds at 44.1kHz using text prompts with a generative model. It is based on latent diffusion, with its latent defined by a fully-convolutional variational autoencoder. The generative model is conditioned on text prompts as well as timing embeddings, allowing for fine control over both the content and length of the generated music and sounds. It is capable of rendering stereo signals of up to 95 sec at 44.1kHz in 8 sec on an A100 GPU. Despite its compute efficiency and fast inference, the proposed model is one of the best in two public text-to-music and -audio benchmarks and, differently from state-of-the-art models, can generate music with structure and stereo sounds.

We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord progression, many of which are non-differentiable which pose a challenge when using them for guided diffusion. We propose Stochastic Control Guidance (SCG), a novel guidance method that only requires forward evaluation of rule functions that can work with pre-trained diffusion models in a plug-and-play way, thus achieving training-free guidance for non-differentiable rules for the first time. Additionally, we introduce a latent diffusion architecture for symbolic music generation with high time resolution, which can be composed with SCG in a plug-and-play fashion. Compared to standard strong baselines in symbolic music generation, this framework demonstrates marked advancements in music quality and rule-based controllability, outperforming current state-of-the-art generators in a variety of settings. For detailed demonstrations, code and model checkpoints, please visit our [project website](https://scg-rule-guided-music.github.io/).

Neuron-level interpretations aim to explain network behaviors and properties by investigating neurons responsive to specific perceptual or structural input patterns. Although there is emerging work in the vision and language domains, none is explored for acoustic models. To bridge the gap, we introduce *AND*, the first **A**udio **N**etwork **D**issection framework that automatically establishes natural language explanations of acoustic neurons based on highly responsive audio. *AND* features the use of LLMs to summarize mutual acoustic features and identities among audio. Extensive experiments are conducted to verify *AND*'s precise and informative descriptions. In addition, we highlight two acoustic model behaviors with analysis by *AND*. First, models discriminate audio with a combination of basic acoustic features rather than high-level abstract concepts. Second, training strategies affect neuron behaviors. Supervised training guides neurons to gradually narrow their attention, while self-supervised learning encourages neurons to be polysemantic for exploring high-level features. Finally, we demonstrate a potential use of *AND* in audio model unlearning by conducting concept-specific pruning based on the descriptions.

Imagine generating a city’s electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched with paired heterogeneous contextual metadata (e.g., weather and location). Current approaches to time series generation often ignore this paired metadata. Additionally, the heterogeneity in metadata poses several practical challenges in adapting existing conditional generation approaches from the image, audio, and video domains to the time series domain. To address this gap, we introduce TIME WEAVER, a novel diffusion-based model that leverages the heterogeneous metadata in the form of categorical, continuous, and even time-variant variables to significantly improve time series generation. Additionally, we show that naive extensions of standard evaluation metrics from the image to the time series domain are insufficient. These metrics do not penalize conditional generation approaches for their poor specificity in reproducing the metadata-specific features in the generated time series. Thus, we innovate a novel evaluation metric that accurately captures the specificity of conditional generation and the realism of the generated time series. We show that TIME WEAVER outperforms state-of-the-art benchmarks, such as Generative Adversarial Networks (GANs), by up to 30% in downstream classification tasks on real-world energy, medical, air quality, and traffic datasets.

Audio generation is a major branch of generative AI research. Compared with prior works in this area that are commonly task-specific with heavy domain knowledge, this paper advocates building universal audio generation models that can handle various tasks in a unified manner. As recent research on large language models (LLMs) has demonstrated their strong ability to handle multiple tasks, this work presents UniAudio, an LLM-based audio generation model that supports a wide range of audio generation tasks. Based on various input conditions, such as phoneme, text description, or audio itself, UniAudio can generate speech, sound, music, and singing voice. The proposed UniAudio is built with 100k hours of multi-source open-available audio data and is scaled to 1B parameters. The audio tokenization method and language model architecture are also specifically designed for both performance and efficiency. Experimentally, UniAuido supports 11 audio generation tasks and achieves competitive results on all tasks consistently. We also show that UniAudio can support new tasks seamlessly via simple fine-tuning.

Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in general. In this work we introduce *D-Flow*, a simple framework for controlling the generation process by differentiating through the flow, optimizing for the source (noise) point. We motivate this framework by our key observation stating that for Diffusion/FM models trained with Gaussian probability paths, differentiating through the generation process projects gradient on the data manifold, implicitly injecting the prior into the optimization process. We validate our framework on linear and non-linear controlled generation problems including: image and audio inverse problems and conditional molecule generation reaching state of the art performance across all.

Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal model for *music* understanding. We detail our process for dataset creation, which involves augmenting the annotations of diverse open-source music datasets and converting them to a unified instruction-tuning format. We propose a multimodal architecture for LLark, integrating a pretrained generative model for music with a pretrained language model. In evaluations on three types of tasks (music understanding, captioning, reasoning), we show that LLark matches or outperforms existing baselines in music understanding, and that humans show a high degree of agreement with its responses in captioning and reasoning tasks. LLark is trained entirely from open-source music data and models, and we make our training code available along with the release of this paper. Additional results and audio examples are at https://bit.ly/llark, and our source code is available at https://github.com/spotify-research/llark.

We propose MusicRL, the first music generation system finetuned from human feedback. Appreciation of text-to-music models is particularly subjective since the concept of musicality as well as the specific intention behind a caption are user-dependent (e.g. a caption such as “upbeat workout music” can map to a retro guitar solo or a technopop beat). Not only this makes supervised training of such models challenging, but it also calls for integrating continuous human feedback in their post-deployment finetuning. MusicRL is a pretrained autoregressive [MusicLM](https://arxiv.org/abs/2301.11325) model of discrete audio tokens finetuned with reinforcement learning to maximize sequence-level rewards. We design reward functions related specifically to text-adherence and audio quality with the help from selected raters, and use those to finetune MusicLM into MusicRL-R. We deploy MusicLM to users and collect a substantial dataset comprising 300,000 pairwise preferences. Using Reinforcement Learning from Human Feedback (RLHF), we train MusicRL-U, the first text-to-music model that incorporates human feedback at scale. Human evaluations show that both MusicRL-R and MusicRL-U are preferred to the baseline. Ultimately, MusicRL-RU combines the two approaches and results in the best model according to human raters. Ablation studies shed light on the musical attributes influencing human preferences, indicating that text adherence and quality only account for a part of it. This underscores the prevalence of subjectivity in musical appreciation and calls for further involvement of human listeners in the finetuning of music generation models. Samples can be found at google-research.github.io/seanet/musiclm/rlhf/.

Music generation schemes using language modeling rely on a vocabulary of audio tokens, generally provided as codes in a discrete latent space learnt by an auto-encoder. Multi-stage quantizers are often employed to produce these tokens, therefore the decoding strategy used for token prediction must be adapted to account for multiple codebooks: either it should model the joint distribution over all codebooks, or fit the product of the codebook marginal distributions. Modelling the joint distribution requires a costly increase in the number of auto-regressive steps, while fitting the product of the marginals yields an inexact model unless the codebooks are mutually independent. In this work, we introduce an independence-promoting loss to regularize the auto-encoder used as the tokenizer in language models for music generation. The proposed loss is a proxy for mutual information based on the maximum mean discrepancy principle, applied in reproducible kernel Hilbert spaces. Our criterion is simple to implement and train, and it is generalizable to other multi-stream codecs. We show that it reduces the statistical dependence between codebooks during auto-encoding. This leads to an increase in the generated music quality when modelling the product of the marginal distributions, while generating audio much faster than the joint distribution model.

In this work, we present DFlow, a novel generative framework that combines Normalizing Flow (NF) with a Denoising AutoEncoder (DAE), for high-fidelity waveform generation. With a tactfully designed structure, DFlow seamlessly integrates the capabilities of both NF and DAE, resulting in a significantly improved performance compared to the standard NF models. Experimental results showcase DFlow's superiority, achieving the highest MOS score among the existing methods on commonly used datasets and the fastest synthesis speed among all likelihood models. We further demonstrate the generalization ability of DFlow by generating high-quality out-of-distribution audio samples, such as singing and music audio. Additionally, we extend the model capacity of DFlow by scaling up both the model size and training set size. Our large-scale universal vocoder, DFlow-XL, achieves highly competitive performance against the best universal vocoder, BigVGAN.

Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterpretable parameters. We propose a text-to-audio generation method that leverages a virtual modular sound synthesizer with only 78 parameters. Synthesizers have long been used by skilled sound designers for media like music and film due to their flexibility and intuitive controls. Our method, CTAG, iteratively updates a synthesizer's parameters to produce high-quality audio renderings of text prompts that can be easily inspected and tweaked. Sounds produced this way are also more abstract, capturing essential conceptual features over fine-grained acoustic details, akin to how simple sketches can vividly convey visual concepts. Our results show how CTAG produces sounds that are distinctive, perceived as artistic, and yet similarly identifiable to recent neural audio synthesis models, positioning it as a valuable and complementary tool.