Text-to-audio (TTA) generation with finegrained control signals, e.g., precise timing control or intelligible speech content, has been explored in recent works.However, constrained by data scarcity, their generation performance at scale is still compromised.In this study, we recast controllable TTA generation as a multi-task learning problem and introduce a progressive diffusion modeling approach, Con-trolAudio.Our method adeptly fits distributions conditioned on more fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy.First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme.Second, at the model training stage, we pretrain a diffusion transformer (DiT) on large-scale text-audio pairs, achieving scalable TTA generation, and then incrementally integrate the timing and phoneme features with unified semantic representations, expanding controllability.Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-tofine sampling nature of DiT.Extensive experiments show that ControlAudio achieves stateof-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations.Demo samples are available at:

Respiratory rate (RR) is a critical health indicator often monitored under inconvenient scenarios, limiting its practicality for continuous monitoring. Photoplethysmography (PPG) sensors, increasingly integrated into wearable devices, offer a chance to continuously estimate RR in a portable manner. In this paper, we propose RespDiff, an end-to-end multi-scale RNN diffusion model for respiratory waveform estimation from PPG signals. RespDiff does not require hand-crafted features or the exclusion of low-quality signal segments, making it suitable for real-world scenarios. The model employs multi-scale encoders, to extract features at different resolutions, and a bidirectional RNN to process PPG signals and generate respiratory waveform. Additionally, a spectral loss term is introduced to optimize the model further. Experiments conducted on the BIDMC dataset demonstrate that RespDiff outperforms notable previous works, achieving a mean absolute error (MAE) of 1.18 bpm for RR estimation while others range from 1.66 to 2.15 bpm, showing its potential for robust and accurate respiratory monitoring in real-world applications.

Diffusion models have achieved remarkable progress on image-to-video (I2V) generation, while their noise-to-data generation process is inherently mismatched with this task, which may lead to suboptimal synthesis quality. In this work, we present FrameBridge. By modeling the frame-to-frames generation process with a bridge model based data-to-data generative process, we are able to fully exploit the information contained in the given image and improve the consistency between the generation process and I2V task. Moreover, we propose two novel techniques toward the two popular settings of training I2V models, respectively. Firstly, we propose SNR-Aligned Fine-tuning (SAF), making the first attempt to fine-tune a diffusion model to a bridge model and, therefore, allowing us to utilize the pre-trained diffusion-based text-to-video (T2V) models. Secondly, we propose neural prior, further improving the synthesis quality of FrameBridge when training from scratch. Experiments conducted on WebVid-2M and UCF-101 demonstrate the superior quality of FrameBridge in comparison with the diffusion counterpart (zero-shot FVD 95 vs. 192 on MSR-VTT and non-zero-shot FVD 122 vs. 171 on UCF-101), and the advantages of our proposed SAF and neural prior for bridge-based I2V models. The project page: https://framebridge-icml.github.io/

Text-to-audio (T2A) generation has achieved promising results with the recent advances in generative models. However, because of the limited quality and quantity of temporally-aligned audio-text pairs, existing T2A methods struggle to handle the complex text prompts that contain precise timing control, e.g., owl hooted at 2.4s-5.2s. Recent works have explored data augmentation techniques or introduced timing conditions as model inputs to enable timing-conditioned 10-second T2A generation, while their synthesis quality is still limited. In this work, we propose a novel training-free timing-controlled T2A framework, FreeAudio, making the first attempt to enable timing-controlled long-form T2A generation, e.g., owl hooted at 2.4s-5.2s and crickets chirping at 0s-24s. Specifically, we first employ an LLM to plan non-overlapping time windows and recaption each with a refined natural language description, based on the input text and timing prompts. Then we introduce: 1) Decoupling & Aggregating Attention Control for precise timing control; 2) Contextual Latent Composition for local smoothness and Reference Guidance for global consistency. Extensive experiments show that: 1) FreeAudio achieves state-of-the-art timing-conditioned T2A synthesis quality among training-free methods and is comparable to leading training-based methods; 2) FreeAudio demonstrates comparable long-form generation quality with training-based Stable Audio and paves the way for timing-controlled long-form T2A synthesis. Demo samples are available at: https://freeaudio.github.io/FreeAudio/.

Audio super-resolution (SR), i.e., upsampling the low-resolution (LR) waveform to the high-resolution (HR) version, has recently been explored with diffusion and bridge models, while previous methods often suffer from sub-optimal upsampling quality due to their uninformative generation prior. Towards high-quality audio super-resolution, we present a new system with latent bridge models (LBMs), where we compress the audio waveform into a continuous latent space and design an LBM to enable a latent-to-latent generation process that naturally matches the LR-to-HR upsampling process, thereby fully exploiting the instructive prior information contained in the LR waveform. To further enhance the training results despite the limited availability of HR samples, we introduce frequency-aware LBMs, where the prior and target frequency are taken as model input, enabling LBMs to explicitly learn an any-to-any upsampling process at the training stage. Furthermore, we design cascaded LBMs and present two prior augmentation strategies, where we make the first attempt to unlock the audio upsampling beyond 48 kHz and empower a seamless cascaded SR process, providing higher flexibility for audio post-production. Comprehensive experimental results evaluated on the VCTK, ESC-50, Song-Describer benchmark datasets and two internal testsets demonstrate that we achieve state-of-the-art objective and perceptual quality for any-to-48 kHz SR across speech, audio, and music signals, as well as setting the first record for any-to-192kHz audio SR. Demo at https://AudioLBM.github.io/.

Text-to-audio (TTA) systems have recently gained attention for their ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn continuous audio representations from contrastive language-audio pretraining (CLAP) embeddings. The pretrained CLAP models enable us to train LDMs with audio embeddings while providing text embeddings as the condition during sampling. By learning the latent representations of audio signals without modelling the cross-modal relationship, AudioLDM improves both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance compared to other open-sourced systems, measured by both objective and subjective metrics. AudioLDM is also the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

Denoising diffusion probabilistic models (diffusion models for short) require a large number of iterations in inference to achieve the generation quality that matches or surpasses the state-of-the-art generative models, which invariably results in slow inference speed. Previous approaches aim to optimize the choice of inference schedule over a few iterations to speed up inference. However, this results in reduced generation quality, mainly because the inference process is optimized separately, without jointly optimizing with the training process. In this paper, we propose InferGrad, a diffusion model for vocoder that incorporates inference process into training, to reduce the inference iterations while maintaining high generation quality. More specifically, during training, we generate data from random noise through a reverse process under inference schedules with a few iterations, and impose a loss to minimize the gap between the generated and ground-truth data samples. Then, unlike existing approaches, the training of InferGrad considers the inference process. The advantages of InferGrad are demonstrated through experiments on the LJSpeech dataset showing that InferGrad achieves better voice quality than the baseline WaveGrad under same conditions while maintaining the same voice quality as the baseline but with 3x speedup (2 iterations for InferGrad vs 6 iterations for WaveGrad).

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtration, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models), the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: $0.128$ vs. $0.157$, MOS: $3.80$ vs. $3.61$). The generated audio samples\footnote{\url{https://speechresearch.github.io/binauralgrad}} and code\footnote{\url{https://github.com/microsoft/NeuralSpeech/tree/master/BinauralGrad}} are available online.

Cuffless technologies provide a convenient platform for remote and continuous blood pressure (BP) monitoring, however, signal recordings employed for cuffless BP estimation, which are based on the electrocardiogram (ECG) and photo-plethysmography (PPG) signals, are frequently corrupted with measurement noise and artefacts. Consequently, even a small portion of abnormal data samples can severely impact the overall signal quality and therefore lead to significantly distorted BP value estimates. To this end, a data-driven model is proposed to infer the beat-to-beat signal quality for the ECG, PPG and BP signal recordings, whereby high-quality and low-quality (outlier) beats are detected using a probabilistic model chosen according to the maximum entropy principle. Physiological rules are also imposed to guarantee that each filtered sample is physiologically meaningful. The advantages of the proposed filtering framework for both systolic blood pressure and diastolic blood pressure estimation are demonstrated through the analysis and estimation of 12,000 clinical BP recordings, consisting of over 200,000 test samples.