Search

Speech synthesis technology has posed a serious threat to speaker verification systems. Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance. However, most of the previously proposed fusion methods require fine-tuning the pretrained models, resulting in excessively long training times and hindering model iteration when facing new speech synthesis technology. To address this issue, this paper proposes a feature fusion method based on the Mixture of Experts, which extracts and integrates features relevant to fake audio detection from layer features, guided by a gating network based on the last layer feature, while freezing the pretrained model. Experiments conducted on the ASVspoof2019 and ASVspoof2021 datasets demonstrate that the proposed method achieves competitive performance compared to those requiring fine-tuning., Comment: submitted to ICASSP2025

In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the specific acoustic properties of speech. To address these limitations, we propose a method called Directional Patch Interaction for Text-to-Speech (DPI-TTS), which builds on DiT and achieves fast training without compromising accuracy. Notably, DPI-TTS employs a low-to-high frequency, frame-by-frame progressive inference approach that aligns more closely with acoustic properties, enhancing the naturalness of the generated speech. Additionally, we introduce a fine-grained style temporal modeling method that further improves speaker style similarity. Experimental results demonstrate that our method increases the training speed by nearly 2 times and significantly outperforms the baseline models., Comment: Submitted to ICASSP2025

Current mainstream audio generation methods primarily rely on simple text prompts, often failing to capture the nuanced details necessary for multi-style audio generation. To address this limitation, the Sound Event Enhanced Prompt Adapter is proposed. Unlike traditional static global style transfer, this method extracts style embedding through cross-attention between text and reference audio for adaptive style control. Adaptive layer normalization is then utilized to enhance the model's capacity to express multiple styles. Additionally, the Sound Event Reference Style Transfer Dataset (SERST) is introduced for the proposed target style audio generation task, enabling dual-prompt audio generation using both text and audio references. Experimental results demonstrate the robustness of the model, achieving state-of-the-art Fr\'echet Distance of 26.94 and KL Divergence of 1.82, surpassing Tango, AudioLDM, and AudioGen. Furthermore, the generated audio shows high similarity to its corresponding audio reference. The demo, code, and dataset are publicly available., Comment: 5 pages, 2 figures, submitted to ICASSP 2025

Currently, Audio Language Models (ALMs) are rapidly advancing due to the developments in large language models and audio neural codecs. These ALMs have significantly lowered the barrier to creating deepfake audio, generating highly realistic and diverse types of deepfake audio, which pose severe threats to society. Consequently, effective audio deepfake detection technologies to detect ALM-based audio have become increasingly critical. This paper investigate the effectiveness of current countermeasure (CM) against ALM-based audio. Specifically, we collect 12 types of the latest ALM-based deepfake audio and utilizing the latest CMs to evaluate. Our findings reveal that the latest codec-trained CM can effectively detect ALM-based audio, achieving 0% equal error rate under most ALM test conditions, which exceeded our expectations. This indicates promising directions for future research in ALM-based deepfake audio detection.

In the current era of Artificial Intelligence Generated Content (AIGC), a Low-Rank Adaptation (LoRA) method has emerged. It uses a plugin-based approach to learn new knowledge with lower parameter quantities and computational costs, and it can be plugged in and out based on the specific sub-tasks, offering high flexibility. However, the current application schemes primarily incorporate LoRA into the pre-introduced conditional parts of the speech models. This fixes the position of LoRA, limiting the flexibility and scalability of its application. Therefore, we propose the Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech (EELE) method. Starting from a general neutral speech model, we do not pre-introduce emotional information but instead use the LoRA plugin to design a flexible adaptive scheme that endows the model with emotional generation capabilities. Specifically, we initially train the model using only neutral speech data. After training is complete, we insert LoRA into different modules and fine-tune the model with emotional speech data to find the optimal insertion scheme. Through experiments, we compare and test the effects of inserting LoRA at different positions within the model and assess LoRA's ability to learn various emotions, effectively proving the validity of our method. Additionally, we explore the impact of the rank size of LoRA and the difference compared to directly fine-tuning the entire model.

In the field of deepfake detection, previous studies focus on using reconstruction or mask and prediction methods to train pre-trained models, which are then transferred to fake audio detection training where the encoder is used to extract features, such as wav2vec2.0 and Masked Auto Encoder. These methods have proven that using real audio for reconstruction pre-training can better help the model distinguish fake audio. However, the disadvantage lies in poor interpretability, meaning it is hard to intuitively present the differences between deepfake and real audio. This paper proposes a noval feature extraction method via color quantisation which constrains the reconstruction to use a limited number of colors for the spectral image-like input. The proposed method ensures reconstructed input differs from the original, which allows for intuitive observation of the focus areas in the spectral reconstruction. Experiments conducted on the ASVspoof2019 dataset demonstrate that the proposed method achieves better classification performance compared to using the original spectral as input and pretraining the recolor network can also benefit the fake audio detection., Comment: accepted by ISCSLP2024

This work evaluates the passivation effectiveness of ultrathin nitride layers (SiNx, AlN, TiN) deposited via atomic layer deposition on CdTe/MgCdTe double heterostructures for solar cell applications. Time-resolved photoluminescence and photoluminescence measurements revealed enhanced carrier lifetimes and reduced surface recombination, indicating improved passivation effectiveness. These results underscore the potential of SiNx as a promising passivation material to improve the efficiency of CdTe solar cells., Comment: 16 pages, 4 figures

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often struggle with inadequate speaker representation accuracy and overfitting, particularly in limited reference speeches scenarios. To address these challenges, we propose an Agile Speaker Representation Reinforcement Learning strategy to enhance speaker similarity in speaker adaptation tasks. ASRRL is the first work to apply reinforcement learning to improve the modeling accuracy of speaker embeddings in speaker adaptation, addressing the challenge of decoupling voice content and timbre. Our approach introduces two action strategies tailored to different reference speeches scenarios. In the single-sentence scenario, a knowledge-oriented optimal routine searching RL method is employed to expedite the exploration and retrieval of refinement information on the fringe of speaker representations. In the few-sentence scenario, we utilize a dynamic RL method to adaptively fuse reference speeches, enhancing the robustness and accuracy of speaker modeling. To achieve optimal results in the target domain, a multi-scale fusion scoring mechanism based reward model that evaluates speaker similarity, speech quality, and intelligibility across three dimensions is proposed, ensuring that improvements in speaker similarity do not compromise speech quality or intelligibility. The experimental results on the LibriTTS and VCTK datasets within mainstream TTS frameworks demonstrate the extensibility and generalization capabilities of the proposed ASRRL method. The results indicate that the ASRRL method significantly outperforms traditional fine-tuning approaches, achieving higher speaker similarity and better overall speech quality with limited reference speeches., Comment: The audio demo is available at https://7xin.github.io/ASRRL/

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper., Comment: ISCSLP 2024 Challenge description and results

This paper presents the development of a speech synthesis system for the LIMMITS'24 Challenge, focusing primarily on Track 2. The objective of the challenge is to establish a multi-speaker, multi-lingual Indic Text-to-Speech system with voice cloning capabilities, covering seven Indian languages with both male and female speakers. The system was trained using challenge data and fine-tuned for few-shot voice cloning on target speakers. Evaluation included both mono-lingual and cross-lingual synthesis across all seven languages, with subjective tests assessing naturalness and speaker similarity. Our system uses the VITS2 architecture, augmented with a multi-lingual ID and a BERT model to enhance contextual language comprehension. In Track 1, where no additional data usage was permitted, our model achieved a Speaker Similarity score of 4.02. In Track 2, which allowed the use of extra data, it attained a Speaker Similarity score of 4.17.

Foley audio, critical for enhancing the immersive experience in multimedia content, faces significant challenges in the AI-generated content (AIGC) landscape. Despite advancements in AIGC technologies for text and image generation, the foley audio dubbing remains rudimentary due to difficulties in cross-modal scene matching and content correlation. Current text-to-audio technology, which relies on detailed and acoustically relevant textual descriptions, falls short in practical video dubbing applications. Existing datasets like AudioSet, AudioCaps, Clotho, Sound-of-Story, and WavCaps do not fully meet the requirements for real-world foley audio dubbing task. To address this, we introduce the Multi-modal Image and Narrative Text Dubbing Dataset (MINT), designed to enhance mainstream dubbing tasks such as literary story audiobooks dubbing, image/silent video dubbing. Besides, to address the limitations of existing TTA technology in understanding and planning complex prompts, a Foley Audio Content Planning, Generation, and Alignment (CPGA) framework is proposed, which includes a content planning module leveraging large language models for complex multi-modal prompts comprehension. Additionally, the training process is optimized using Proximal Policy Optimization based reinforcement learning, significantly improving the alignment and auditory realism of generated foley audio. Experimental results demonstrate that our approach significantly advances the field of foley audio dubbing, providing robust solutions for the challenges of multi-modal dubbing. Even when utilizing the relatively lightweight GPT-2 model, our framework outperforms open-source multimodal large models such as LLaVA, DeepSeek-VL, and Moondream2. The dataset is available at https://github.com/borisfrb/MINT .

With the proliferation of Large Language Model (LLM) based deepfake audio, there is an urgent need for effective detection methods. Previous deepfake audio generation methods typically involve a multi-step generation process, with the final step using a vocoder to predict the waveform from handcrafted features. However, LLM-based audio is directly generated from discrete neural codecs in an end-to-end generation process, skipping the final step of vocoder processing. This poses a significant challenge for current audio deepfake detection (ADD) models based on vocoder artifacts. To effectively detect LLM-based deepfake audio, we focus on the core of the generation process, the conversion from neural codec to waveform. We propose Codecfake dataset, which is generated by seven representative neural codec methods. Experiment results show that codec-trained ADD models exhibit a 41.406% reduction in average equal error rate compared to vocoder-trained ADD models on the Codecfake test set., Comment: Accepted by INTERSPEECH 2024. arXiv admin note: substantial text overlap with arXiv:2405.04880

Text-to-Audio (TTA) aims to generate audio that corresponds to the given text description, playing a crucial role in media production. The text descriptions in TTA datasets lack rich variations and diversity, resulting in a drop in TTA model performance when faced with complex text. To address this issue, we propose a method called Portable Plug-in Prompt Refiner, which utilizes rich knowledge about textual descriptions inherent in large language models to effectively enhance the robustness of TTA acoustic models without altering the acoustic training set. Furthermore, a Chain-of-Thought that mimics human verification is introduced to enhance the accuracy of audio descriptions, thereby improving the accuracy of generated content in practical applications. The experiments show that our method achieves a state-of-the-art Inception Score (IS) of 8.72, surpassing AudioGen, AudioLDM and Tango., Comment: accepted by INTERSPEECH2024

Although current fake audio detection approaches have achieved remarkable success on specific datasets, they often fail when evaluated with datasets from different distributions. Previous studies typically address distribution shift by focusing on using extra data or applying extra loss restrictions during training. However, these methods either require a substantial amount of data or complicate the training process. In this work, we propose a stable learning-based training scheme that involves a Sample Weight Learning (SWL) module, addressing distribution shift by decorrelating all selected features via learning weights from training samples. The proposed portable plug-in-like SWL is easy to apply to multiple base models and generalizes them without using extra data during training. Experiments conducted on the ASVspoof datasets clearly demonstrate the effectiveness of SWL in generalizing different models across three evaluation datasets from different distributions., Comment: accepted by INTERSPEECH2024

The generalization of Fake Audio Detection (FAD) is critical due to the emergence of new spoofing techniques. Traditional FAD methods often focus solely on distinguishing between genuine and known spoofed audio. We propose a Genuine-Focused Learning (GFL) framework guided, aiming for highly generalized FAD, called GFL-FAD. This method incorporates a Counterfactual Reasoning Enhanced Representation (CRER) based on audio reconstruction using the Mask AutoEncoder (MAE) architecture to accurately model genuine audio features. To reduce the influence of spoofed audio during training, we introduce a genuine audio reconstruction loss, maintaining the focus on learning genuine data features. In addition, content-related bottleneck (BN) features are extracted from the MAE to supplement the knowledge of the original audio. These BN features are adaptively fused with CRER to further improve robustness. Our method achieves state-of-the-art performance with an EER of 0.25% on ASVspoof2019 LA., Comment: Accepted by INTERSPEECH 2024

Visual tracking fundamentally involves regressing the state of the target in each frame of a video. Despite significant progress, existing regression-based trackers still tend to experience failures and inaccuracies. To enhance the precision of target estimation, this paper proposes a tracking technique based on robust regression. Firstly, we introduce a novel robust linear regression estimator, which achieves favorable performance when the error vector follows i.i.d Gaussian-Laplacian distribution. Secondly, we design an iterative process to quickly solve the problem of outliers. In fact, the coefficients are obtained by Iterative Gradient Descent and Threshold Selection algorithm (IGDTS). In addition, we expend IGDTS to a generative tracker, and apply IGDTS-distance to measure the deviation between the sample and the model. Finally, we propose an update scheme to capture the appearance changes of the tracked object and ensure that the model is updated correctly. Experimental results on several challenging image sequences show that the proposed tracker outperformance existing trackers.

Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve the generalization capability. However, the data heterogeneity between sources may lead models to gradually forget previously acquired knowledge when undergoing cross-training to adapt to new tasks or data sources. We argue that integrating personalized and global knowledge to gather information from multiple perspectives could potentially improve performance. To achieve this goal, this paper presents a novel approach that enhances federated learning through a cross-training scheme incorporating multi-view information. Specifically, the proposed method, termed FedCT, includes three main modules, where the consistency-aware knowledge broadcasting module aims to optimize model assignment strategies, which enhances collaborative advantages between clients and achieves an efficient federated learning process. The multi-view knowledge-guided representation learning module leverages fused prototypical knowledge from both global and local views to enhance the preservation of local knowledge before and after model exchange, as well as to ensure consistency between local and global knowledge. The mixup-based feature augmentation module aggregates rich information to further increase the diversity of feature spaces, which enables the model to better discriminate complex samples. Extensive experiments were conducted on four datasets in terms of performance comparison, ablation study, in-depth analysis and case study. The results demonstrated that FedCT alleviates knowledge forgetting from both local and global views, which enables it outperform state-of-the-art methods.

The neighbor-based method has become a powerful tool to handle the outlier detection problem, which aims to infer the abnormal degree of the sample based on the compactness of the sample and its neighbors. However, the existing methods commonly focus on designing different processes to locate outliers in the dataset, while the contributions of different types neighbors to outlier detection has not been well discussed. To this end, this paper studies the neighbor in the existing outlier detection algorithms and a taxonomy is introduced, which uses the three-level components of information, neighbor and methodology to define hybrid methods. This taxonomy can serve as a paradigm where a novel neighbor-based outlier detection method can be proposed by combining different components in this taxonomy. A large number of comparative experiments were conducted on synthetic and real-world datasets in terms of performance comparison and case study, and the results show that reverse K-nearest neighbor based methods achieve promising performance and dynamic selection method is suitable for working in high-dimensional space. Notably, it is verified that rationally selecting components from this taxonomy may create an algorithms superior to existing methods.

Learning with noisy labels has become an effective strategy for enhancing the robustness of models, which enables models to better tolerate inaccurate data. Existing methods either focus on optimizing the loss function to mitigate the interference from noise, or design procedures to detect potential noise and correct errors. However, their effectiveness is often compromised in representation learning due to the dilemma where models overfit to noisy labels. To address this issue, this paper proposes a relation modeling and distillation framework that models inter-sample relationships via self-supervised learning and employs knowledge distillation to enhance understanding of latent associations, which mitigate the impact of noisy labels. Specifically, the proposed method, termed RMDNet, includes two main modules, where the relation modeling (RM) module implements the contrastive learning technique to learn representations of all data, an unsupervised approach that effectively eliminates the interference of noisy tags on feature extraction. The relation-guided representation learning (RGRL) module utilizes inter-sample relation learned from the RM module to calibrate the representation distribution for noisy samples, which is capable of improving the generalization of the model in the inference phase. Notably, the proposed RMDNet is a plug-and-play framework that can integrate multiple methods to its advantage. Extensive experiments were conducted on two datasets, including performance comparison, ablation study, in-depth analysis and case study. The results show that RMDNet can learn discriminative representations for noisy data, which results in superior performance than the existing methods.

With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for generalized detection methods. ALM-based deepfake audio currently exhibits widespread, high deception, and type versatility, posing a significant challenge to current audio deepfake detection (ADD) models trained solely on vocoded data. To effectively detect ALM-based deepfake audio, we focus on the mechanism of the ALM-based audio generation method, the conversion from neural codec to waveform. We initially construct the Codecfake dataset, an open-source large-scale dataset, including 2 languages, over 1M audio samples, and various test conditions, focus on ALM-based audio detection. As countermeasure, to achieve universal detection of deepfake audio and tackle domain ascent bias issue of original SAM, we propose the CSAM strategy to learn a domain balanced and generalized minima. In our experiments, we first demonstrate that ADD model training with the Codecfake dataset can effectively detects ALM-based audio. Furthermore, our proposed generalization countermeasure yields the lowest average Equal Error Rate (EER) of 0.616% across all test conditions compared to baseline models. The dataset and associated code are available online.

Recently, it has been found that a $Q$-ball can amplify waves incident upon it, due to rotation in the internal space and the interaction of the two modes in the complex scalar field. While the spherically symmetric 3D case has been investigated previously, here we explore the 3D axi-symmetric case, which is numerically much more challenging. The difficulty comes because a partial wave expansion is needed, and the different partial waves can not be separated, for either the background spinning Q-ball solution or the perturbative scattering on top of it. A relaxation method and a high dimensional shooting method are applied to compute the Q-ball solutions and the amplification factors respectively. We also classify the behavior of the amplification factors and we discuss their bounds and the superradiance criteria., Comment: 20 pages, 14 figures

The physics of individual Q-balls and interactions between multiple Q-balls are well-studied in classical numerical simulations. Interesting properties and phenomena have been discovered, involving stability, forces, collisions and swapping of charge between different components of multi-Q-ball systems. We investigate these phenomena in quantum field theory, including quantum corrections to leading order in a 2PI coupling expansion, the inhomogeneous Hartree approximation. The presence of quantum modes and new decay channels allows the mean-field Q-ball to exchange charge with the quantum modes, and also alters the charge swapping frequencies of the composite Q-balls. It is also observed that the periodic exchanges between the mean-field and quantum modes tend to be quenched by collisions between Q-balls. We illustrate how the classical limit arises through a scaling of the Q-ball potential, making quantum corrections negligible for large-amplitude Q-balls., Comment: 29 pages, 18 figures

This paper presents a French text-to-speech synthesis system for the Blizzard Challenge 2023. The challenge consists of two tasks: generating high-quality speech from female speakers and generating speech that closely resembles specific individuals. Regarding the competition data, we conducted a screening process to remove missing or erroneous text data. We organized all symbols except for phonemes and eliminated symbols that had no pronunciation or zero duration. Additionally, we added word boundary and start/end symbols to the text, which we have found to improve speech quality based on our previous experience. For the Spoke task, we performed data augmentation according to the competition rules. We used an open-source G2P model to transcribe the French texts into phonemes. As the G2P model uses the International Phonetic Alphabet (IPA), we applied the same transcription process to the provided competition data for standardization. However, due to compiler limitations in recognizing special symbols from the IPA chart, we followed the rules to convert all phonemes into the phonetic scheme used in the competition data. Finally, we resampled all competition audio to a uniform sampling rate of 16 kHz. We employed a VITS-based acoustic model with the hifigan vocoder. For the Spoke task, we trained a multi-speaker model and incorporated speaker information into the duration predictor, vocoder, and flow layers of the model. The evaluation results of our system showed a quality MOS score of 3.6 for the Hub task and 3.4 for the Spoke task, placing our system at an average level among all participating teams.

Recently, it has been realized that in some systems internal space rotation can induce energy amplification for scattering waves, similar to rotation in real space. Particularly, it has been shown that energy extraction is possible for a Q-ball, a stationary non-topological soliton that is coherently rotating in its field space. In this paper, we generalize the analysis to the case of boson stars, and show that the same energy extraction mechanism still works for boson stars., Comment: 10 pages, 6 figures; v2: refs added and clarified

The superconducting linear accelerator is a highly flexiable facility for modern scientific discoveries, necessitating weekly reconfiguration and tuning. Accordingly, minimizing setup time proves essential in affording users with ample experimental time. We propose a trend-based soft actor-critic(TBSAC) beam control method with strong robustness, allowing the agents to be trained in a simulated environment and applied to the real accelerator directly with zero-shot. To validate the effectiveness of our method, two different typical beam control tasks were performed on China Accelerator Facility for Superheavy Elements (CAFe II) and a light particle injector(LPI) respectively. The orbit correction tasks were performed in three cryomodules in CAFe II seperately, the time required for tuning has been reduced to one-tenth of that needed by human experts, and the RMS values of the corrected orbit were all less than 1mm. The other transmission efficiency optimization task was conducted in the LPI, our agent successfully optimized the transmission efficiency of radio-frequency quadrupole(RFQ) to over $85\%$ within 2 minutes. The outcomes of these two experiments offer substantiation that our proposed TBSAC approach can efficiently and effectively accomplish beam commissioning tasks while upholding the same standard as skilled human experts. As such, our method exhibits potential for future applications in other accelerator commissioning fields.

We compare the transport properties of a well-characterized hydrogen plasma for low and high current ion beams. The energy-loss of low current beams can be well understood, within the framework of current stopping power models. However, for high current proton beams, significant energy-loss reduction and collimation is observed in the experiment. We have developed a new particle-in-cell code, which includes both collective electromagnetic effects and collisional interactions. Our simulations indicate that resistive magnetic fields, induced by the transport of an intense proton beam, act to collimate the proton beam and simultaneously deplete the local plasma density along the beam path. This in turn causes the energy-loss reduction detected in the experiment.