PyTorchKR Papers

최신 논문

총 124편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2412.01169공식 코드 · Papers with Code

OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to handle the joint distribution of multiple modalities. It outperforms previous any-to-any models on a wide range of tasks, such as text-to-image and text-to-audio synthesis. Our work offers three key contributions: First, we extend RF to a multi-modal setting and introduce a novel guidance mechanism, enabling users to flexibly control the alignment between different modalities in the generated outputs. Second, we propose a novel architecture that extends the text-to-image MMDiT architecture of Stable Diffusion 3 and enables audio and text generation. The extended modules can be efficiently pretrained individually and merged with the vanilla text-to-image MMDiT for fine-tuning. Lastly, we conduct a comprehensive study on the design choices of rectified flow transformers for large-scale audio and text generation, providing valuable insights into optimizing performance across diverse modalities. The Code will be available at https://github.com/jacklishufan/OmniFlows.

arXiv:2411.14642

VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space

Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and interpretability. Leveraging the AudioMNIST dataset, consisting of human utterances of decimal digits (0-9), our method employs a two-step architecture: first, a scalable vector quantized autoencoder (VQ-VAE) that compresses audio spectrograms into discrete latent representations, and second, a decoder-only transformer that learns the probability model of these latents. Trained transformer generates similar latent sequences, convertible to audio spectrograms by the VQ-VAE decoder, from which we generate fake utterances. Interpreting statistical and perceptual quality of the fakes, depending on the dimension and the extrinsic information of the latent space, enables guided improvements in larger, commercial generative models. As a valuable tool for understanding and refining audio synthesis, our results demonstrate VQalAttent's capacity to generate intelligible speech samples with limited computational resources, while the modularity and transparency of the training pipeline helps easily correlate the analytics with modular modifications, hence providing insights for the more complex models.

arXiv:2410.16785

Annotation-Free MIDI-to-Audio Synthesis via Concatenative Synthesis and Generative Refinement

Recent MIDI-to-audio synthesis methods using deep neural networks have successfully generated high-quality, expressive instrumental tracks. However, these methods require MIDI annotations for supervised training, limiting the diversity of instrument timbres and expression styles in the output. We propose CoSaRef, a MIDI-to-audio synthesis method that does not require MIDI-audio paired datasets. CoSaRef first generates a synthetic audio track using concatenative synthesis based on MIDI input, then refines it with a diffusion-based deep generative model trained on datasets without MIDI annotations. This approach improves the diversity of timbres and expression styles. Additionally, it allows detailed control over timbres and expression through audio sample selection and extra MIDI design, similar to traditional functions in digital audio workstations. Experiments showed that CoSaRef could generate realistic tracks while preserving fine-grained timbre control via one-shot samples. Moreover, despite not being supervised on MIDI annotation, CoSaRef outperformed the state-of-the-art timbre-controllable method based on MIDI supervision in both objective and subjective evaluation.

arXiv:2410.05739

Array2BR: An End-to-End Noise-immune Binaural Audio Synthesis from Microphone-array Signals

Telepresence technology aims to provide an immersive virtual presence for remote conference applications, and it is extremely important to synthesize high-quality binaural audio signals for this aim. Because the ambient noise is often inevitable in practical application scenarios, it is highly desired that binaural audio signals without noise can be obtained from microphone-array signals directly. For this purpose, this paper proposes a new end-to-end noise-immune binaural audio synthesis framework from microphone-array signals, abbreviated as Array2BR, and experimental results show that binaural cues can be correctly mapped and noise can be well suppressed simultaneously using the proposed framework. Compared with existing methods, the proposed method achieved better performance in terms of both objective and subjective metric scores.

arXiv:2410.04324공식 코드 · Papers with Code

Where are we in audio deepfake detection? A systematic analysis over generative and detection models

Recent advances in Text-to-Speech (TTS) and Voice-Conversion (VC) using generative Artificial Intelligence (AI) technology have made it possible to generate high-quality and realistic human-like audio. This poses growing challenges in distinguishing AI-synthesized speech from the genuine human voice and could raise concerns about misuse for impersonation, fraud, spreading misinformation, and scams. However, existing detection methods for AI-synthesized audio have not kept pace and often fail to generalize across diverse datasets. In this paper, we introduce SONAR, a synthetic AI-Audio Detection Framework and Benchmark, aiming to provide a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content. SONAR includes a novel evaluation dataset sourced from 9 diverse audio synthesis platforms, including leading TTS providers and state-of-the-art TTS models. It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based detection systems. Through extensive experiments, (1) we reveal the limitations of existing detection methods and demonstrate that foundation models exhibit stronger generalization capabilities, likely due to their model size and the scale and quality of pretraining data. (2) Speech foundation models demonstrate robust cross-lingual generalization capabilities, maintaining strong performance across diverse languages despite being fine-tuned solely on English speech data. This finding also suggests that the primary challenges in audio deepfake detection are more closely tied to the realism and quality of synthetic audio rather than language-specific characteristics. (3) We explore the effectiveness and efficiency of few-shot fine-tuning in improving generalization, highlighting its potential for tailored applications, such as personalized detection systems for specific entities or individuals.

arXiv:2409.13894

PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models

Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant data. However, their broader adoption is limited by high computational costs and large memory footprints. Post-training quantization (PTQ) offers a promising approach to mitigate these challenges by reducing model complexity through low-bandwidth parameters. Yet, direct application of PTQ to diffusion models can degrade synthesis quality due to accumulated quantization noise across multiple denoising steps, particularly in conditional tasks like text-to-audio synthesis. This work introduces PTQ4ADM, a novel framework for quantizing audio diffusion models(ADMs). Our key contributions include (1) a coverage-driven prompt augmentation method and (2) an activation-aware calibration set generation algorithm for text-conditional ADMs. These techniques ensure comprehensive coverage of audio aspects and modalities while preserving synthesis fidelity. We validate our approach on TANGO, Make-An-Audio, and AudioLDM models for text-conditional audio generation. Extensive experiments demonstrate PTQ4ADM's capability to reduce the model size by up to 70\% while achieving synthesis quality metrics comparable to full-precision models($<$5\% increase in FD scores). We show that specific layers in the backbone network can be quantized to 4-bit weights and 8-bit activations without significant quality loss. This work paves the way for more efficient deployment of ADMs in resource-constrained environments.

arXiv:2409.12477공식 코드 · Papers with Code

ViolinDiff: Enhancing Expressive Violin Synthesis with Pitch Bend Conditioning

Modeling the natural contour of fundamental frequency (F0) plays a critical role in music audio synthesis. However, transcribing and managing multiple F0 contours in polyphonic music is challenging, and explicit F0 contour modeling has not yet been explored for polyphonic instrumental synthesis. In this paper, we present ViolinDiff, a two-stage diffusion-based synthesis framework. For a given violin MIDI file, the first stage estimates the F0 contour as pitch bend information, and the second stage generates mel spectrogram incorporating these expressive details. The quantitative metrics and listening test results show that the proposed model generates more realistic violin sounds than the model without explicit pitch bend modeling. Audio samples are available online: daewoung.github.io/ViolinDiff-Demo.

arXiv:2409.07390

D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as synthetic speech has become indistinguishable from natural human speech. Several speech-generation programs are utilized for malicious purposes, especially impersonating individuals through phone calls. Therefore, detecting fake audio is crucial to maintain social security and safeguard the integrity of information. Recent research has proposed a D-CAPTCHA system based on the challenge-response protocol to differentiate fake phone calls from real ones. In this work, we study the resilience of this system and introduce a more robust version, D-CAPTCHA++, to defend against fake calls. Specifically, we first expose the vulnerability of the D-CAPTCHA system under transferable imperceptible adversarial attack. Secondly, we mitigate such vulnerability by improving the robustness of the system by using adversarial training in D-CAPTCHA deepfake detectors and task classifiers.

arXiv:2409.06135

Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis

Foley is a term commonly used in filmmaking, referring to the addition of daily sound effects to silent films or videos to enhance the auditory experience. Video-to-Audio (V2A), as a particular type of automatic foley task, presents inherent challenges related to audio-visual synchronization. These challenges encompass maintaining the content consistency between the input video and the generated audio, as well as the alignment of temporal and loudness properties within the video. To address these issues, we construct a controllable video-to-audio synthesis model, termed Draw an Audio, which supports multiple input instructions through drawn masks and loudness signals. To ensure content consistency between the synthesized audio and target video, we introduce the Mask-Attention Module (MAM), which employs masked video instruction to enable the model to focus on regions of interest. Additionally, we implement the Time-Loudness Module (TLM), which uses an auxiliary loudness signal to ensure the synthesis of sound that aligns with the video in both loudness and temporal dimensions. Furthermore, we have extended a large-scale V2A dataset, named VGGSound-Caption, by annotating caption prompts. Extensive experiments on challenging benchmarks across two large-scale V2A datasets verify Draw an Audio achieves the state-of-the-art. Project page: https://yannqi.github.io/Draw-an-Audio/.

arXiv:2409.02451

Fast, High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP

Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal processing (DDSP) is a parameter-efficient framework for audio synthesis. Therefore, integrating low-dimensional EMA features with DDSP can significantly enhance the computational efficiency of speech synthesis. In this paper, we propose a fast, high-quality, and parameter-efficient DDSP articulatory vocoder that can synthesize speech from EMA, F0, and loudness. We incorporate several techniques to solve the harmonics / noise imbalance problem, and add a multi-resolution adversarial loss for better synthesis quality. Our model achieves a transcription word error rate (WER) of 6.67% and a mean opinion score (MOS) of 3.74, with an improvement of 1.63% and 0.16 compared to the state-of-the-art (SOTA) baseline. Our DDSP vocoder is 4.9x faster than the baseline on CPU during inference, and can generate speech of comparable quality with only 0.4M parameters, in contrast to the 9M parameters required by the SOTA.

arXiv:2408.12658

Hierarchical Generative Modeling of Melodic Vocal Contours in Hindustani Classical Music

Hindustani music is a performance-driven oral tradition that exhibits the rendition of rich melodic patterns. In this paper, we focus on generative modeling of singers' vocal melodies extracted from audio recordings, as the voice is musically prominent within the tradition. Prior generative work in Hindustani music models melodies as coarse discrete symbols which fails to capture the rich expressive melodic intricacies of singing. Thus, we propose to use a finely quantized pitch contour, as an intermediate representation for hierarchical audio modeling. We propose GaMaDHaNi, a modular two-level hierarchy, consisting of a generative model on pitch contours, and a pitch contour to audio synthesis model. We compare our approach to non-hierarchical audio models and hierarchical models that use a self-supervised intermediate representation, through a listening test and qualitative analysis. We also evaluate audio model's ability to faithfully represent the pitch contour input using Pearson correlation coefficient. By using pitch contours as an intermediate representation, we show that our model may be better equipped to listen and respond to musicians in a human-AI collaborative setting by highlighting two potential interaction use cases (1) primed generation, and (2) coarse pitch conditioning.

arXiv:2408.11915

Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound

Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor alignment and controllability, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as an intuitive condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope closely related to audio semantics, acts as a temporal event feature to guide audio generation from video. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Source code, model weights and demos are available on our companion website. (https://jnwnlee.github.io/video-foley-demo)

arXiv:2407.20592

EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos

We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, music, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics addresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode and process paired audio-video data to make them suitable for generation. The encoded data is then used to train a model that can generate an audio track that captures the semantics of the input video. Our proposed SyncroNet builds on top of ControlNet to provide control signals that enables generation of temporally synchronized audio. Extensive evaluations and a comprehensive user study show that our model outperforms existing work in audio quality, and in our proposed synchronization evaluation method. Furthermore, we demonstrate downstream applications of our model in improving video summarization.

arXiv:2407.14212

Braille-to-Speech Generator: Audio Generation Based on Joint Fine-Tuning of CLIP and Fastspeech2

An increasing number of Chinese people are troubled by different degrees of visual impairment, which has made the modal conversion between a single image or video frame in the visual field and the audio expressing the same information a research hotspot. Deep learning technologies such as OCR+Vocoder and Im2Wav enable English audio synthesis or image-to-sound matching in a self-supervised manner. However, the audio data used for training is limited and English is not universal for visually impaired people with different educational levels. Therefore, for the sake of solving the problems of data volume and language applicability to improve the reading efficiency of visually impaired people, a set of image-to-speech framework CLIP-KNN-Fastspeech2 based on the Chinese context was constructed. The framework integrates multiple basic models and adopts the strategy of independent pre-training and joint fine-tuning. First, the Chinese CLIP and Fastspeech2 text-to-speech models were pre-trained on two public datasets, MUGE and Baker, respectively, and their convergence was verified. Subsequently, joint fine-tuning was performed using a self-built Braille image dataset. Experimental results on multiple public datasets such as VGGSound, Flickr8k, ImageHear, and the self-built Braille dataset BIT-DP show that the model has improved objective indicators such as BLEU4,FAD(Fr\'echet Audio Distance), WER(Word Error Ratio), and even inference speed. This verifies that the constructed model still has the ability to synthesize high-quality speech under limited data, and also proves the effectiveness of the joint training strategy that integrates multiple basic models.

arXiv:2407.10471

GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis

Amid the burgeoning development of generative models like diffusion models, the task of differentiating synthesized audio from its natural counterpart grows more daunting. Deepfake detection offers a viable solution to combat this challenge. Yet, this defensive measure unintentionally fuels the continued refinement of generative models. Watermarking emerges as a proactive and sustainable tactic, preemptively regulating the creation and dissemination of synthesized content. Thus, this paper, as a pioneer, proposes the generative robust audio watermarking method (Groot), presenting a paradigm for proactively supervising the synthesized audio and its source diffusion models. In this paradigm, the processes of watermark generation and audio synthesis occur simultaneously, facilitated by parameter-fixed diffusion models equipped with a dedicated encoder. The watermark embedded within the audio can subsequently be retrieved by a lightweight decoder. The experimental results highlight Groot's outstanding performance, particularly in terms of robustness, surpassing that of the leading state-of-the-art methods. Beyond its impressive resilience against individual post-processing attacks, Groot exhibits exceptional robustness when facing compound attacks, maintaining an average watermark extraction accuracy of around 95%.

arXiv:2407.10468공식 코드 · Papers with Code

LiteFocus: Accelerated Diffusion Inference for Long Audio Synthesis

Latent diffusion models have shown promising results in audio generation, making notable advancements over traditional methods. However, their performance, while impressive with short audio clips, faces challenges when extended to longer audio sequences. These challenges are due to model's self-attention mechanism and training predominantly on 10-second clips, which complicates the extension to longer audio without adaptation. In response to these issues, we introduce a novel approach, LiteFocus that enhances the inference of existing audio latent diffusion models in long audio synthesis. Observed the attention pattern in self-attention, we employ a dual sparse form for attention calculation, designated as same-frequency focus and cross-frequency compensation, which curtails the attention computation under same-frequency constraints, while enhancing audio quality through cross-frequency refillment. LiteFocus demonstrates substantial reduction on inference time with diffusion-based TTA model by 1.99x in synthesizing 80-second audio clips while also obtaining improved audio quality.

arXiv:2406.19388

Taming Data and Transformers for Audio Generation

The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of $83.2$, a $3.2\%$ improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale, GenAu obtains significant improvements of $4.7\%$ in FAD score, $11.1\%$ in IS, and $13.5\%$ in CLAP score. Our code, model checkpoints, and dataset are publicly available.

arXiv:2406.08920

AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis

Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing binaural audio. However, in addition to low efficiency originating from heavy NeRF rendering, these methods all have a limited ability of characterizing the entire scene environment such as room geometry, material properties, and the spatial relation between the listener and sound source. To address these issues, we propose a novel Audio-Visual Gaussian Splatting (AV-GS) model. To obtain a material-aware and geometry-aware condition for audio synthesis, we learn an explicit point-based scene representation with an audio-guidance parameter on locally initialized Gaussian points, taking into account the space relation from the listener and sound source. To make the visual scene model audio adaptive, we propose a point densification and pruning strategy to optimally distribute the Gaussian points, with the per-point contribution in sound propagation (e.g., more points needed for texture-less wall surfaces as they affect sound path diversion). Extensive experiments validate the superiority of our AV-GS over existing alternatives on the real-world RWAS and simulation-based SoundSpaces datasets.

arXiv:2406.07237

CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems

Current state-of-the-art (SOTA) codec-based audio synthesis systems can mimic anyone's voice with just a 3-second sample from that specific unseen speaker. Unfortunately, malicious attackers may exploit these technologies, causing misuse and security issues. Anti-spoofing models have been developed to detect fake speech. However, the open question of whether current SOTA anti-spoofing models can effectively counter deepfake audios from codec-based speech synthesis systems remains unanswered. In this paper, we curate an extensive collection of contemporary SOTA codec models, employing them to re-create synthesized speech. This endeavor leads to the creation of CodecFake, the first codec-based deepfake audio dataset. Additionally, we verify that anti-spoofing models trained on commonly used datasets cannot detect synthesized speech from current codec-based speech generation systems. The proposed CodecFake dataset empowers these models to counter this challenge effectively.

arXiv:2406.05128공식 코드 · Papers with Code

Differentiable Time-Varying Linear Prediction in the Context of End-to-End Analysis-by-Synthesis

Training the linear prediction (LP) operator end-to-end for audio synthesis in modern deep learning frameworks is slow due to its recursive formulation. In addition, frame-wise approximation as an acceleration method cannot generalise well to test time conditions where the LP is computed sample-wise. Efficient differentiable sample-wise LP for end-to-end training is the key to removing this barrier. We generalise the efficient time-invariant LP implementation from the GOLF vocoder to time-varying cases. Combining this with the classic source-filter model, we show that the improved GOLF learns LP coefficients and reconstructs the voice better than its frame-wise counterparts. Moreover, in our listening test, synthesised outputs from GOLF scored higher in quality ratings than the state-of-the-art differentiable WORLD vocoder.