This paper presents a tutorial-style survey and implementation guide of BemaGANv2, an advanced GAN-based vocoder designed for high-fidelity and long-term audio generation. Built upon the original BemaGAN architecture, BemaGANv2 incorporates major architectural innovations by replacing traditional ResBlocks in the generator with the Anti-aliased Multi-Periodicity composition (AMP) module, which internally applies the Snake activation function to better model periodic structures. In the discriminator framework, we integrate the Multi-Envelope Discriminator (MED), a novel architecture we originally proposed, to extract rich temporal envelope features crucial for periodicity detection. Coupled with the Multi-Resolution Discriminator (MRD), this combination enables more accurate modeling of long-range dependencies in audio. We systematically evaluate various discriminator configurations, including MSD + MED, MSD + MRD, and MPD + MED + MRD, using objective metrics (FAD, SSIM, PLCC, MCD) and subjective evaluations (MOS, SMOS). This paper also provides a comprehensive tutorial on the model architecture, training methodology, and implementation to promote reproducibility. The code and pre-trained models are available at: https://github.com/dinhoitt/BemaGANv2.
Drum one-shot samples are crucial for music production, particularly in sound design and electronic music. This paper introduces Drum One-Shot Extraction, a task in which the goal is to extract drum one-shots that are present in the music mixture. To facilitate this, we propose the Random Mixture One-shot Dataset (RMOD), comprising large-scale, randomly arranged music mixtures paired with corresponding drum one-shot samples. Our proposed model, Drum One- Shot Extractor (DOSE), leverages neural audio codec language models for end-to-end extraction, bypassing traditional source separation steps. Additionally, we introduce a novel onset loss, designed to encourage accurate prediction of the initial transient of drum one-shots, which is essential for capturing timbral characteristics. We compare this approach against a source separation-based extraction method as a baseline. The results, evaluated using Frechet Audio Distance (FAD) and Multi-Scale Spectral loss (MSS), demonstrate that DOSE, enhanced with onset loss, outperforms the baseline, providing more accurate and higher-quality drum one-shots from music mixtures. The code, model checkpoint, and audio examples are available at https://github.com/HSUNEH/DOSE
Despite significant recent advances in generative acoustic text-to-music (TTM) modeling, robust evaluation of these models lags behind, relying in particular on the popular Fr\'echet Audio Distance (FAD). In this work, we rigorously study the design space of reference-based divergence metrics for evaluating TTM models through (1) designing four synthetic meta-evaluations to measure sensitivity to particular musical desiderata, and (2) collecting and evaluating on MusicPrefs, the first open-source dataset of human preferences for TTM systems. We find that not only is the standard FAD setup inconsistent on both synthetic and human preference data, but that nearly all existing metrics fail to effectively capture desiderata, and are only weakly correlated with human perception. We propose a new metric, the MAUVE Audio Divergence (MAD), computed on representations from a self-supervised audio embedding model. We find that this metric effectively captures diverse musical desiderata (average rank correlation 0.84 for MAD vs. 0.49 for FAD and also correlates more strongly with MusicPrefs (0.62 vs. 0.14).
We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques. We provide theoretical insights and geometric intuitions for our approach in comparison to ScoreDec as well as another recent work that uses flow matching, and conduct ablation studies on our proposed components. We show that FlowDec is a competitive alternative to the recent GAN-dominated stream of neural codecs, achieving FAD scores better than those of the established GAN-based codec DAC and listening test scores that are on par, and producing qualitatively more natural reconstructions for speech and harmonic structures in music.
Although being widely adopted for evaluating generated audio signals, the Fr\'echet Audio Distance (FAD) suffers from significant limitations, including reliance on Gaussian assumptions, sensitivity to sample size, and high computational complexity. As an alternative, we introduce the Kernel Audio Distance (KAD), a novel, distribution-free, unbiased, and computationally efficient metric based on Maximum Mean Discrepancy (MMD). Through analysis and empirical validation, we demonstrate KAD's advantages: (1) faster convergence with smaller sample sizes, enabling reliable evaluation with limited data; (2) lower computational cost, with scalable GPU acceleration; and (3) stronger alignment with human perceptual judgments. By leveraging advanced embeddings and characteristic kernels, KAD captures nuanced differences between real and generated audio. Open-sourced in the kadtk toolkit, KAD provides an efficient, reliable, and perceptually aligned benchmark for evaluating generative audio models.
In this paper we introduce the Frechet Music Distance (FMD), a novel evaluation metric for generative symbolic music models, inspired by the Frechet Inception Distance (FID) in computer vision and Frechet Audio Distance (FAD) in generative audio. FMD calculates the distance between distributions of reference and generated symbolic music embeddings, capturing abstract musical features. We validate FMD across several datasets and models. Results indicate that FMD effectively differentiates model quality, providing a domain-specific metric for evaluating symbolic music generation, and establishing a reproducible standard for future research in symbolic music modeling.
The complex nature of musical emotion introduces inherent bias in both recognition and generation, particularly when relying on a single audio encoder, emotion classifier, or evaluation metric. In this work, we conduct a study on Music Emotion Recognition (MER) and Emotional Music Generation (EMG), employing diverse audio encoders alongside Frechet Audio Distance (FAD), a reference-free evaluation metric. Our study begins with a benchmark evaluation of MER, highlighting the limitations of using a single audio encoder and the disparities observed across different measurements. We then propose assessing MER performance using FAD derived from multiple encoders to provide a more objective measure of musical emotion. Furthermore, we introduce an enhanced EMG approach designed to improve both the variability and prominence of generated musical emotion, thereby enhancing its realism. Additionally, we investigate the differences in realism between the emotions conveyed in real and synthetic music, comparing our EMG model against two baseline models. Experimental results underscore the issue of emotion bias in both MER and EMG and demonstrate the potential of using FAD and diverse audio encoders to evaluate musical emotion more objectively and effectively.
Most music generation models directly generate a single music mixture. To allow for more flexible and controllable generation, the Multi-Source Diffusion Model (MSDM) has been proposed to model music as a mixture of multiple instrumental sources (e.g. piano, drums, bass, and guitar). Its goal is to use one single diffusion model to generate mutually-coherent music sources, that are then mixed to form the music. Despite its capabilities, MSDM is unable to generate music with rich melodies and often generates empty sounds. Its waveform diffusion approach also introduces significant Gaussian noise artifacts that compromise audio quality. In response, we introduce a Multi-Source Latent Diffusion Model (MSLDM) that employs Variational Autoencoders (VAEs) to encode each instrumental source into a distinct latent representation. By training a VAE on all music sources, we efficiently capture each source's unique characteristics in a "source latent." The source latents are concatenated and our diffusion model learns this joint latent space. This approach significantly enhances the total and partial generation of music by leveraging the VAE's latent compression and noise-robustness. The compressed source latent also facilitates more efficient generation. Subjective listening tests and Frechet Audio Distance (FAD) scores confirm that our model outperforms MSDM, showcasing its practical and enhanced applicability in music generation systems. We also emphasize that modeling sources is more effective than direct music mixture modeling. Codes and models are available at https://github.com/XZWY/MSLDM. Demos are available at https://xzwy.github.io/MSLDMDemo/.
Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency of audio generation remains an essential issue to be addressed, especially for AR models that are incorporated in large language models (LLMs). In this paper, we analyze the token length of audio tokenization and propose a novel \textbf{S}cale-level \textbf{A}udio \textbf{T}okenizer (SAT), with improved residual quantization. Based on SAT, a scale-level \textbf{A}coustic \textbf{A}uto\textbf{R}egressive (AAR) modeling framework is further proposed, which shifts the next-token AR prediction to next-scale AR prediction, significantly reducing the training cost and inference time. To validate the effectiveness of the proposed approach, we comprehensively analyze design choices and demonstrate the proposed AAR framework achieves a remarkable \textbf{35}$\times$ faster inference speed and +\textbf{1.33} Fr\'echet Audio Distance (FAD) against baselines on the AudioSet benchmark. Code: \url{https://github.com/qiuk2/AAR}.
LiDAR-based vision systems are integral for 3D object detection, which is crucial for autonomous navigation. However, they suffer from performance degradation in adverse weather conditions due to the quality deterioration of LiDAR point clouds. Fusing LiDAR with the weather-robust 4D radar sensor is expected to solve this problem. However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR includes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) technique to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and Intra-Modal ({IM}2 ) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in real-world adverse weather conditions.
Music is a universal language that can communicate emotions and feelings. It forms an essential part of the whole spectrum of creative media, ranging from movies to social media posts. Machine learning models that can synthesize music are predominantly conditioned on textual descriptions of it. Inspired by how musicians compose music not just from a movie script, but also through visualizations, we propose MeLFusion, a model that can effectively use cues from a textual description and the corresponding image to synthesize music. MeLFusion is a text-to-music diffusion model with a novel "visual synapse", which effectively infuses the semantics from the visual modality into the generated music. To facilitate research in this area, we introduce a new dataset MeLBench, and propose a new evaluation metric IMSM. Our exhaustive experimental evaluation suggests that adding visual information to the music synthesis pipeline significantly improves the quality of generated music, measured both objectively and subjectively, with a relative gain of up to 67.98% on the FAD score. We hope that our work will gather attention to this pragmatic, yet relatively under-explored research area.
Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models. These systems use multimodal text-audio representation models, such as Contrastive Language-Audio Pretraining (CLAP), whose objective is to map corresponding audio and text prompts into a joint embedding space. AudioLDM, a text-to-audio model, was the winner of the DCASE2023 task 7 Foley sound synthesis challenge. The winning system fine-tuned the model for specific audio classes and applied a post-filtering method using CLAP similarity scores between output audio and input text at inference time, requiring the generation of extra samples, thus reducing data generation efficiency. We introduce a new loss term to enhance Foley sound generation in AudioLDM without post-filtering. This loss term uses a new module based on the CLAP mode-Latent CLAP encode-to align the latent diffusion output with real audio in a shared CLAP embedding space. Our experiments demonstrate that our method effectively reduces the Frechet Audio Distance (FAD) score of the generated audio and eliminates the need for post-filtering, thus enhancing generation efficiency.
The growing popularity of generative music models underlines the need for perceptually relevant, objective music quality metrics. The Frechet Audio Distance (FAD) is commonly used for this purpose even though its correlation with perceptual quality is understudied. We show that FAD performance may be hampered by sample size bias, poor choice of audio embeddings, or the use of biased or low-quality reference sets. We propose reducing sample size bias by extrapolating scores towards an infinite sample size. Through comparisons with MusicCaps labels and a listening test we identify audio embeddings and music reference sets that yield FAD scores well-correlated with acoustic and musical quality. Our results suggest that per-song FAD can be useful to identify outlier samples and predict perceptual quality for a range of music sets and generative models. Finally, we release a toolkit that allows adapting FAD for generative music evaluation.
In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection. AMSP-UOD specifically addresses the impact of non-ideal imaging factors on detection accuracy in complex underwater environments. To mitigate the influence of noise on object detection performance, we propose AMSP Vortex Convolution (AMSP-VConv) to disrupt the noise distribution, enhance feature extraction capabilities, effectively reduce parameters, and improve network robustness. We design the Feature Association Decoupling Cross Stage Partial (FAD-CSP) module, which strengthens the association of long and short range features, improving the network performance in complex underwater environments. Additionally, our sophisticated post-processing method, based on Non-Maximum Suppression (NMS) with aspect-ratio similarity thresholds, optimizes detection in dense scenes, such as waterweed and schools of fish, improving object detection accuracy. Extensive experiments on the URPC and RUOD datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of accuracy and noise immunity. AMSP-UOD proposes an innovative solution with the potential for real-world applications. Our code is available at https://github.com/zhoujingchun03/AMSP-UOD.
A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints. However, there is a mismatch problem in using a model trained with complete utterances for streaming inference with partial input. We demonstrate that speech representations extracted at the end of a streaming input are significantly different from those extracted from a complete utterance. To address this issue, we propose a new approach called Future-Aware Streaming Translation (FAST) that adapts an offline ST model for streaming input. FAST includes a Future-Aware Inference (FAI) strategy that incorporates future context through a trainable masked embedding, and a Future-Aware Distillation (FAD) framework that transfers future context from an approximation of full speech to streaming input. Our experiments on the MuST-C EnDe, EnEs, and EnFr benchmarks show that FAST achieves better trade-offs between translation quality and latency than strong baselines. Extensive analyses suggest that our methods effectively alleviate the aforementioned mismatch problem between offline training and online inference.
We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal Diffusion model (i.e., MM-Diffusion), with two-coupled denoising autoencoders. In contrast to existing single-modal diffusion models, MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Two subnets for audio and video learn to gradually generate aligned audio-video pairs from Gaussian noises. To ensure semantic consistency across modalities, we propose a novel random-shift based attention block bridging over the two subnets, which enables efficient cross-modal alignment, and thus reinforces the audio-video fidelity for each other. Extensive experiments show superior results in unconditional audio-video generation, and zero-shot conditional tasks (e.g., video-to-audio). In particular, we achieve the best FVD and FAD on Landscape and AIST++ dancing datasets. Turing tests of 10k votes further demonstrate dominant preferences for our model. The code and pre-trained models can be downloaded at https://github.com/researchmm/MM-Diffusion.
Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual representations in encode phase or improving the decoding ability. However, the long-tailed problem hinders these attempts at low-frequency tokens, which rarely occur but carry critical semantics, playing a vital role in the detailed generation. In this paper, we introduce a novel Refined Semantic enhancement method towards Frequency Diffusion (RSFD), a captioning model that constantly perceives the linguistic representation of the infrequent tokens. Concretely, a Frequency-Aware Diffusion (FAD) module is proposed to comprehend the semantics of low-frequency tokens to break through generation limitations. In this way, the caption is refined by promoting the absorption of tokens with insufficient occurrence. Based on FAD, we design a Divergent Semantic Supervisor (DSS) module to compensate for the information loss of high-frequency tokens brought by the diffusion process, where the semantics of low-frequency tokens is further emphasized to alleviate the long-tailed problem. Extensive experiments indicate that RSFD outperforms the state-of-the-art methods on two benchmark datasets, i.e., MSR-VTT and MSVD, demonstrate that the enhancement of low-frequency tokens semantics can obtain a competitive generation effect. Code is available at https://github.com/lzp870/RSFD.
We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architecture on mel-spectrograms of preprocessed versions of the audio samples. The mel-spectrograms generated by the model are then inverted back to the audio domain. As a result, our generated samples substantially improve upon the baseline provided by the competition from a qualitative and quantitative perspective for all emotions. More precisely, even for our worst-performing emotion (awe), we obtain an FAD of 1.76 compared to the baseline of 4.81 (as a reference, the FAD between the train/validation sets for awe is 0.776).
This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. The adopted approach combines Variational Autoencoders with Generative Adversarial Networks to construct meaningful representations of the source audio and produce realistic generations of the target audio and is applied to the Flickr 8k Audio dataset for transferring the vocal timbre between speakers and the URMP dataset for transferring the musical timbre between instruments. Furthermore, variations of the adopted approach are trained, and generalised performance is compared using the metrics SSIM (Structural Similarity Index) and FAD (Frech\'et Audio Distance). It was found that a many-to-many approach supersedes a one-to-one approach in terms of reconstructive capabilities, and that the adoption of a basic over a bottleneck residual block design is more suitable for enriching content information about a latent space. It was also found that the decision on whether cyclic loss takes on a variational autoencoder or vanilla autoencoder approach does not have a significant impact on reconstructive and adversarial translation aspects of the model.
Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.