DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model

Text-to-audio (TTA), which generates audio signals from textual descriptions, has received huge attention in recent years. However, recent works focused on text to monaural audio only. As we know, spatial audio provides more immersive auditory experience than monaural audio, e.g. in virtual reality. To address this issue, we propose a text-to-spatial-audio (TTSA) generation framework named DualSpec.Specifically, it first trains variational autoencoders (VAEs) for extracting the latent acoustic representations from sound event audio. Then, given text that describes sound events and event directions, the proposed method uses the encoder of a pretrained large language model to transform the text into text features. Finally, it trains a diffusion model from the latent acoustic representations and text features for the spatial audio generation. In the inference stage, only the text description is needed to generate spatial audio. Particularly, to improve the synthesis quality and azimuth accuracy of the spatial sound events simultaneously, we propose to use two kinds of acoustic features. One is the Mel spectrograms which is good for improving the synthesis quality, and the other is the short-time Fourier transform spectrograms which is good at improving the azimuth accuracy. We provide a pipeline of constructing spatial audio dataset with text prompts, for the training of the VAEs and diffusion model. We also introduce new spatial-aware evaluation metrics to quantify the azimuth errors of the generated spatial audio recordings. Experimental results demonstrate that the proposed method can generate spatial audio with high directional and event consistency.

UniForm: A Unified Diffusion Transformer for Audio-Video Generation

As a natural multimodal content, audible video delivers an immersive sensory experience. Consequently, audio-video generation systems have substantial potential. However, existing diffusion-based studies mainly employ relatively independent modules for generating each modality, which lack exploration of shared-weight generative modules. This approach may under-use the intrinsic correlations between audio and visual modalities, potentially resulting in sub-optimal generation quality. To address this, we propose UniForm, a unified diffusion transformer designed to enhance cross-modal consistency. By concatenating auditory and visual information, UniForm learns to generate audio and video simultaneously within a unified latent space, facilitating the creation of high-quality and well-aligned audio-visual pairs. Extensive experiments demonstrate the superior performance of our method in joint audio-video generation, audio-guided video generation, and video-guided audio generation tasks. Our demos are available at https://uniform-t2av.github.io/.

Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR

Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the target speech. However, imperfections in these masks often result in over-/under-suppression of target/non-target speech, degrading perceptual quality. Generative methods, by contrast, re-synthesize target speech based on the mixture and target speaker cues, achieving superior perceptual quality. Nevertheless, these methods often overlook speech intelligibility, leading to alterations or loss of semantic content in the re-synthesized speech. Inspired by the Whisper model's success in target speaker ASR, we propose a generative TSE framework based on the pre-trained Whisper model to address the above issues. This framework integrates semantic modeling with flow-based acoustic modeling to achieve both high intelligibility and perceptual quality. Results from multiple benchmarks demonstrate that the proposed method outperforms existing generative and discriminative baselines. We present speech samples on our demo page.

Speaker Contrastive Learning for Source Speaker Tracing

As a form of biometric authentication technology, the security of speaker verification systems is of utmost importance. However, SV systems are inherently vulnerable to various types of attacks that can compromise their accuracy and reliability. One such attack is voice conversion, which modifies a persons speech to sound like another person by altering various vocal characteristics. This poses a significant threat to SV systems. To address this challenge, the Source Speaker Tracing Challenge in IEEE SLT2024 aims to identify the source speaker information in manipulated speech signals. Specifically, SSTC focuses on source speaker verification against voice conversion to determine whether two converted speech samples originate from the same source speaker. In this study, we propose a speaker contrastive learning-based approach for source speaker tracing to learn the latent source speaker information in converted speech. To learn a more source-speaker-related representation, we employ speaker contrastive loss during the training of the embedding extractor. This speaker contrastive loss helps identify the true source speaker embedding among several distractor speaker embeddings, enabling the embedding extractor to learn the potentially possessing source speaker information present in the converted speech. Experiments demonstrate that our proposed speaker contrastive learning system achieves the lowest EER of 16.788% on the challenge test set, securing first place in the challenge.

Rethinking the Output Architecture for Sound Source Localization

Sound source localization (SSL) involves estimating the direction of arrival (DOA) of a sound signal. The output space of the DOA estimation is continuous, suggesting that regression may be the most appropriate formulation for DOA. However, in practice, converting the DOA estimation into a classification problem often results in better performance than the regression formulation, since that classification problems are generally easier to model, and are more robust in handling noise and uncertainty than regression problems. In the classification formulation of DOA, the output space is discretized into several intervals, each of which is treated as a class. These classes exhibit strong inter-class correlation, with their mutual-similarity increasing when they approach each other and being ordered. However, this property is not sufficiently explored. To exploit these property, we propose a soft label distribution, named Unbiased Label Distribution (ULD), for eliminating the quantization error of the training target and further taking the inter-class similarity into strong consideration. We further introduce two loss functions, named the Negative Log Absolute Error (NLAE) loss function and {Mean Squared Error loss function without activation (MSE(wo))}, for the soft label family. Finally, we design a new decoding method to map the predicted distribution to sound source locations, called Weighted Adjacent Decoding (WAD). It uses the weighted sum of the probabilities of the peak classes and their adjacent classes in the predicted distribution for decoding. Experimental results show that the proposed method achieves the state-of-the-art performance, and the WAD decoding method is able to even breakthrough the quantization error limits of existing decoding methods.

Diffusion-Based Adversarial Purification for Speaker Verification

Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make ASV produce wrong decisions. This poses a significant threat to the security and reliability of ASV systems. To address this issue, we propose a Diffusion-Based Adversarial Purification (DAP) method that enhances the robustness of ASV systems against such adversarial attacks. Our method leverages a conditional denoising diffusion probabilistic model to effectively purify the adversarial examples and mitigate the impact of perturbations. DAP first introduces controlled noise into adversarial examples, and then performs a reverse denoising process to reconstruct clean audio. Experimental results demonstrate the efficacy of the proposed DAP in enhancing the security of ASV and meanwhile minimizing the distortion of the purified audio signals.

Spatial-temporal Graph Based Multi-channel Speaker Verification With Ad-hoc Microphone Arrays

The performance of speaker verification degrades significantly in adverse acoustic environments with strong reverberation and noise. To address this issue, this paper proposes a spatial-temporal graph convolutional network (GCN) method for the multi-channel speaker verification with ad-hoc microphone arrays. It includes a feature aggregation block and a channel selection block, both of which are built on graphs. The feature aggregation block fuses speaker features among different time and channels by a spatial-temporal GCN. The graph-based channel selection block discards the noisy channels that may contribute negatively to the system. The proposed method is flexible in incorporating various kinds of graphs and prior knowledge. We compared the proposed method with six representative methods in both real-world and simulated environments. Experimental results show that the proposed method achieves a relative equal error rate (EER) reduction of $\mathbf{15.39\%}$ lower than the strongest referenced method in the simulated datasets, and $\mathbf{17.70\%}$ lower than the latter in the real datasets. Moreover, its performance is robust across different signal-to-noise ratios and reverberation time.

Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays

Recently, an end-to-end two-dimensional sound source localization algorithm with ad-hoc microphone arrays formulates the sound source localization problem as a classification problem. The algorithm divides the target indoor space into a set of local areas, and predicts the local area where the speaker locates. However, the local areas are encoded by one-hot code, which may lose the connections between the local areas due to quantization errors. In this paper, we propose a new soft label coding method, named label smoothing, for the classification-based two-dimensional sound source location with ad-hoc microphone arrays. The core idea is to take the geometric connection between the classes into the label coding process.The first one is named static soft label coding (SSLC), which modifies the one-hot codes into soft codes based on the distances between the local areas. Because SSLC is handcrafted which may not be optimal, the second one, named dynamic soft label coding (DSLC), further rectifies SSLC, by learning the soft codes according to the statistics of the predictions produced by the classification-based localization model in the training stage. Experimental results show that the proposed methods can effectively improve the localization accuracy.

Optimizing Quantum Federated Learning Based on Federated Quantum Natural Gradient Descent

Quantum federated learning (QFL) is a quantum extension of the classical federated learning model across multiple local quantum devices. An efficient optimization algorithm is always expected to minimize the communication overhead among different quantum participants. In this work, we propose an efficient optimization algorithm, namely federated quantum natural gradient descent (FQNGD), and further, apply it to a QFL framework that is composed of a variational quantum circuit (VQC)-based quantum neural networks (QNN). Compared with stochastic gradient descent methods like Adam and Adagrad, the FQNGD algorithm admits much fewer training iterations for the QFL to get converged. Moreover, it can significantly reduce the total communication overhead among local quantum devices. Our experiments on a handwritten digit classification dataset justify the effectiveness of the FQNGD for the QFL framework in terms of a faster convergence rate on the training set and higher accuracy on the test set.

Interpretable Spectrum Transformation Attacks to Speaker Recognition

The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e. \textit{transfer-based} black-box attacks, the transferability of the adversarial voices is not only far from satisfactory, but also lacks interpretable basis. To address these issues, in this paper, we propose a general framework, named spectral transformation attack based on modified discrete cosine transform (STA-MDCT), to improve the transferability of the adversarial voices to a black-box victim model. Specifically, we first apply MDCT to the input voice. Then, we slightly modify the energy of different frequency bands for capturing the salient regions of the adversarial noise in the time-frequency domain that are critical to a successful attack. Unlike existing approaches that operate voices in the time domain, the proposed framework operates voices in the time-frequency domain, which improves the interpretability, transferability, and imperceptibility of the attack. Moreover, it can be implemented with any gradient-based attackers. To utilize the advantage of model ensembling, we not only implement STA-MDCT with a single white-box surrogate model, but also with an ensemble of surrogate models. Finally, we visualize the saliency maps of adversarial voices by the class activation maps (CAM), which offers an interpretable basis to transfer-based attacks in speaker recognition for the first time. Extensive comparison results with five representative attackers show that the CAM visualization clearly explains the effectiveness of STA-MDCT, and the weaknesses of the comparison methods; the proposed method outperforms the comparison methods by a large margin.