Abstract:Text-guided diffusion models catalyze a paradigm shift in audio generation, facilitating the adaptability of source audio to conform to specific textual prompts. Recent advancements introduce inversion techniques, like DDIM inversion, to zero-shot editing, exploiting pre-trained diffusion models for audio modification. Nonetheless, our investigation exposes that DDIM inversion suffers from an accumulation of errors across each diffusion step, undermining its efficacy. And the lack of attention control hinders the fine-grained manipulations of music. To counteract these limitations, we introduce the \textit{Disentangled Inversion} technique, which is designed to disentangle the diffusion process into triple branches, thereby magnifying their individual capabilities for both precise editing and preservation. Furthermore, we propose the \textit{Harmonized Attention Control} framework, which unifies the mutual self-attention and cross-attention with an additional Harmonic Branch to achieve the desired composition and structural information in the target music. Collectively, these innovations comprise the \textit{Disentangled Inversion Control (DIC)} framework, enabling accurate music editing whilst safeguarding structural integrity. To benchmark audio editing efficacy, we introduce \textit{ZoME-Bench}, a comprehensive music editing benchmark hosting 1,100 samples spread across 10 distinct editing categories, which facilitates both zero-shot and instruction-based music editing tasks. Our method demonstrates unparalleled performance in edit fidelity and essential content preservation, outperforming contemporary state-of-the-art inversion techniques.
Abstract:Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality omni joint representations would be a step toward co-processing more diverse multimodal information. In this work, we present OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters, which support 3D, audio, image, and language inputs. Due to the scarcity of data pairs across all modalities, instead of training large models from scratch, we propose remapping and binding the spaces of various pre-trained specialist models together. This approach enables "scaling up" by indirectly increasing the model parameters and the amount of seen data. To effectively integrate various spaces, we dynamically assign weights to different spaces by learning routers with two objectives: cross-modal overall alignment and language representation decoupling. Notably, since binding and routing spaces both only require lightweight networks, OmniBind is extremely training-efficient. Learning the largest 30B model requires merely unpaired unimodal data and approximately 3 days on a single 8-4090 node. Extensive experiments demonstrate the versatility and superiority of OmniBind as an omni representation model, highlighting its great potential for diverse applications, such as any-query and composable multimodal understanding.
Abstract: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.
Abstract:The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high audio reconstruction quality. The key idea is to reduce the modality heterogeneity between text and audio by compressing the audio modality into a well-trained LLMs token space. Thus, the audio representation can be viewed as a new \textit{foreign language}, and LLMs can learn the new \textit{foreign language} with several demonstrations. In experiments, we investigate the performance of the proposed approach across multiple audio understanding and generation tasks, \textit{e.g.} speech emotion classification, audio classification, text-to-speech generation, speech enhancement, etc. The experimental results demonstrate that the LLMs equipped with the proposed LLM-Codec, named as UniAudio 1.5, prompted by only a few examples, can achieve the expected functions in simple scenarios. It validates the feasibility and effectiveness of the proposed cross-modal in-context learning approach. To facilitate research on few-shot audio task learning and multi-modal LLMs, we have open-sourced the LLM-Codec model.
Abstract:Speech-to-singing voice conversion (STS) task always suffers from data scarcity, because it requires paired speech and singing data. Compounding this issue are the challenges of content-pitch alignment and the suboptimal quality of generated outputs, presenting significant hurdles in STS research. This paper presents SVPT, an STS approach boosted by a self-supervised singing voice pre-training model. We leverage spoken language model techniques to tackle the rhythm alignment problem and the in-context learning capability to achieve zero-shot conversion. We adopt discrete-unit random resampling and pitch corruption strategies, enabling training with unpaired singing data and thus mitigating the issue of data scarcity. SVPT also serves as an effective backbone for singing voice synthesis (SVS), offering insights into scaling up SVS models. Experimental results indicate that SVPT delivers notable improvements in both STS and SVS endeavors. Audio samples are available at https://speech2sing.github.io.
Abstract:In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style, merely based on a few seconds of audio prompt and a simple textual style description prompt. Prior zero-shot TTS models and controllable TTS models either could only mimic the speaker's voice without further control and adjustment capabilities or were unrelated to speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging new task-a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and utilizes bidirectional attention and mask-based parallel decoding to capture corresponding codec representations in a discrete decoupling codec space. Moreover, we discovered the issue of text style controllability in a many-to-many mapping fashion and proposed the Style Mixture Semantic Density (SMSD) model to resolve this problem. SMSD module which is based on Gaussian mixture density networks, is designed to enhance the fine-grained partitioning and sampling capabilities of style semantic information and generate speech with more diverse styles. In terms of experiments, we make available a controllable model toolkit called ControlToolkit with a new style controllable dataset, some replicated baseline models and propose new metrics to evaluate both the control capability and the quality of generated audio in ControlSpeech. The relevant ablation studies validate the necessity of each component in ControlSpeech is necessary. We hope that ControlSpeech can establish the next foundation paradigm of controllable speech synthesis. The relevant code and demo are available at https://github.com/jishengpeng/ControlSpeech .
Abstract:Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds and limiting their application in text-to-audio generation deployment. In this work, we introduce AudioLCM, a novel consistency-based model tailored for efficient and high-quality text-to-audio generation. AudioLCM integrates Consistency Models into the generation process, facilitating rapid inference through a mapping from any point at any time step to the trajectory's initial point. To overcome the convergence issue inherent in LDMs with reduced sample iterations, we propose the Guided Latent Consistency Distillation with a multi-step Ordinary Differential Equation (ODE) solver. This innovation shortens the time schedule from thousands to dozens of steps while maintaining sample quality, thereby achieving fast convergence and high-quality generation. Furthermore, to optimize the performance of transformer-based neural network architectures, we integrate the advanced techniques pioneered by LLaMA into the foundational framework of transformers. This architecture supports stable and efficient training, ensuring robust performance in text-to-audio synthesis. Experimental results on text-to-sound generation and text-to-music synthesis tasks demonstrate that AudioLCM needs only 2 iterations to synthesize high-fidelity audios, while it maintains sample quality competitive with state-of-the-art models using hundreds of steps. AudioLCM enables a sampling speed of 333x faster than real-time on a single NVIDIA 4090Ti GPU, making generative models practically applicable to text-to-audio generation deployment. Our extensive preliminary analysis shows that each design in AudioLCM is effective.
Abstract:Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transformer and channel-level cross-modal feature fusion with strong temporal alignment, our model generates audio that is highly synchronized with the input video. Furthermore, through reflow and one-step distillation with guided vector field, our model can generate decent audio in a few, or even only one sampling step. Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment on VGGSound, with alignment accuracy reaching 97.22%, and 6.2% improvement in inception score over the strong diffusion-based baseline. Audio samples are available at http://frieren-v2a.github.io .
Abstract:Note-level Automatic Singing Voice Transcription (AST) converts singing recordings into note sequences, facilitating the automatic annotation of singing datasets for Singing Voice Synthesis (SVS) applications. Current AST methods, however, struggle with accuracy and robustness when used for practical annotation. This paper presents ROSVOT, the first robust AST model that serves SVS, incorporating a multi-scale framework that effectively captures coarse-grained note information and ensures fine-grained frame-level segmentation, coupled with an attention-based pitch decoder for reliable pitch prediction. We also established a comprehensive annotation-and-training pipeline for SVS to test the model in real-world settings. Experimental findings reveal that ROSVOT achieves state-of-the-art transcription accuracy with either clean or noisy inputs. Moreover, when trained on enlarged, automatically annotated datasets, the SVS model outperforms its baseline, affirming the capability for practical application. Audio samples are available at https://rosvot.github.io.
Abstract:Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In this work, we propose FreeBind, an idea that treats multimodal representation spaces as basic units, and freely augments pre-trained unified space by integrating knowledge from extra expert spaces via "space bonds". Specifically, we introduce two kinds of basic space bonds: 1) Space Displacement Bond and 2) Space Combination Bond. Based on these basic bonds, we design Complex Sequential & Parallel Bonds to effectively integrate multiple spaces simultaneously. Benefiting from the modularization concept, we further propose a coarse-to-fine customized inference strategy to flexibly adjust the enhanced unified space for different purposes. Experimentally, we bind ImageBind with extra image-text and audio-text expert spaces, resulting in three main variants: ImageBind++, InternVL_IB, and InternVL_IB++. These resulting spaces outperform ImageBind on 5 audio-image-text downstream tasks across 9 datasets. Moreover, via customized inference, it even surpasses the advanced audio-text and image-text expert spaces.