Adversarial Attacks and Robust Defenses in Speaker Embedding based Zero-Shot Text-to-Speech System

Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces imperceptible perturbations to the original speaker's audio waveform, leading to synthesized speech sounds like another person. This vulnerability poses significant security risks, including speaker identity spoofing and unauthorized voice manipulation. This paper investigates two primary defense strategies to address these threats: adversarial training and adversarial purification. Adversarial training enhances the model's robustness by integrating adversarial examples during the training process, thereby improving resistance to such attacks. Adversarial purification, on the other hand, employs diffusion probabilistic models to revert adversarially perturbed audio to its clean form. Experimental results demonstrate that these defense mechanisms can significantly reduce the impact of adversarial perturbations, enhancing the security and reliability of speaker embedding based zero-shot TTS systems in adversarial environments.

BiSinger: Bilingual Singing Voice Synthesis

Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual pop SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.

VoiceLens: Controllable Speaker Generation and Editing with Flow

Currently, many multi-speaker speech synthesis and voice conversion systems address speaker variations with an embedding vector. Modeling it directly allows new voices outside of training data to be synthesized. GMM based approaches such as Tacospawn are favored in literature for this generation task, but there are still some limitations when difficult conditionings are involved. In this paper, we propose VoiceLens, a semi-supervised flow-based approach, to model speaker embedding distributions for multi-conditional speaker generation. VoiceLens maps speaker embeddings into a combination of independent attributes and residual information. It allows new voices associated with certain attributes to be \textit{generated} for existing TTS models, and attributes of known voices to be meaningfully \textit{edited}. We show in this paper, VoiceLens displays an unconditional generation capacity that is similar to Tacospawn while obtaining higher controllability and flexibility when used in a conditional manner. In addition, we show synthesizing less noisy speech from known noisy speakers without re-training the TTS model is possible via solely editing their embeddings with a SNR conditioned VoiceLens model. Demos are available at sos1sos2sixteen.github.io/voicelens.

BrickPal: Augmented Reality-based Assembly Instructions for Brick Models

The assembly instruction is a mandatory component of Lego-like brick sets.The conventional production of assembly instructions requires a considerable amount of manual fine-tuning, which is intractable for casual users and customized brick sets.Moreover, the traditional paper-based instructions lack expressiveness and interactivity.To tackle the two problems above, we present BrickPal, an augmented reality-based system, which visualizes assembly instructions in an augmented reality head-mounted display. It utilizes Natural Language Processing (NLP) techniques to generate plausible assembly sequences, and provide real-time guidance in the AR headset.Our user study demonstrates BrickPal's effectiveness at assisting users in brick assembly compared to traditional assembly methods. Additionally, the NLP algorithm-generated assembly sequences achieve the same usability with manually adapted sequences.

On the Application of Uplink/Downlink Decoupled Access in Heterogeneous Mobile Edge Computing

Mobile edge computing (MEC) is a key player in low latency 5G networks with the task to resolve the conflict between computationally-intensive mobile applications and resource-limited mobile devices (MDs). As such, there has been intense interest in this topic, especially in multi-user single-server and homogeneous multi-server scenarios. However, the research in the heterogeneous multi-server scenario is limited, where the servers are located at small base-stations (SBSs), macro base-stations (MBSs), or the cloud with different computing and communication capabilities. On the other hand, computational-tasks offloading is limited by the type of MD-BS association with almost all previous works focusing on offloading the MD's computational tasks to the MEC servers/cloudlets at its serving BS. However, in multi-BS association, or downlink/uplink decoupled (DUDe) scenarios, an MD can be served by multiple BSs and hence has multiple offloading choices. Motivated by this, we proposed a joint BS association and subchannel allocation algorithm based on a student-project allocation (SPA) matching approach to minimize the network sum-latency, which break the constraint that one MD must connect to the same BS in the UL and DL, and jointly consider the communication and computational disparity of SBS and MBS cloudlets in heterogeneous MEC networks. Moreover, an optimal power allocation scheme is proposed to optimize the system performance subject to the predefined quality of service constraints. Our results show that the proposed scheme is superior to benchmark techniques in enabling effective use of the computational and communication resources in heterogeneous MEC networks.