Beilong Tang

Bang Zeng, Beilong Tang, Wang Xiang et al.

Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE and SE systems are based on discriminative modeling and have shown strong interference suppression ability, but they often remain limited in perceptual quality and naturalness. To address this issue, we first introduce LauraTSE, a generative TSE model built on an autoregressive decoder-only language model. Although generative modeling is promising for quality enhancement, purely generative TSE may suffer from hallucination, content drift, and limited controllability in complex acoustic conditions. We therefore propose a discriminative-generative two-stage framework, where a discriminative front-end first produces target-related representations with strong interference suppression, and a generative back-end then reconstructs high-quality speech in the neural audio codec representation space. This design combines the controllability of discriminative extraction with the reconstruction capability of generative modeling. We further investigate several collaboration strategies for the two-stage framework, including front-end freezing, joint fine-tuning, SI-SDR regularization, and autoregressive/non-autoregressive inference. Experimental results on both TSE and SE benchmarks show that the proposed framework achieves a better balance among perceptual quality, intelligibility, and speaker consistency than purely discriminative or purely generative baselines.

Jiaxiang Geng, Beilong Tang, Boyan Zhang et al.

In this demo, we introduce FedCampus, a privacy-preserving mobile application for smart \underline{campus} with \underline{fed}erated learning (FL) and federated analytics (FA). FedCampus enables cross-platform on-device FL/FA for both iOS and Android, supporting continuously models and algorithms deployment (MLOps). Our app integrates privacy-preserving processed data via differential privacy (DP) from smartwatches, where the processed parameters are used for FL/FA through the FedCampus backend platform. We distributed 100 smartwatches to volunteers at Duke Kunshan University and have successfully completed a series of smart campus tasks featuring capabilities such as sleep tracking, physical activity monitoring, personalized recommendations, and heavy hitters. Our project is opensourced at https://github.com/FedCampus/FedCampus_Flutter. See the FedCampus video at https://youtu.be/k5iu46IjA38.

Beilong Tang, Bang Zeng, Ming Li

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. Experimental results show that TSELM achieves excellent results in speech quality and comparable results in speech intelligibility.

Sichang He, Beilong Tang, Boyan Zhang et al.

We present FedKit, a federated learning (FL) system tailored for cross-platform FL research on Android and iOS devices. FedKit pipelines cross-platform FL development by enabling model conversion, hardware-accelerated training, and cross-platform model aggregation. Our FL workflow supports flexible machine learning operations (MLOps) in production, facilitating continuous model delivery and training. We have deployed FedKit in a real-world use case for health data analysis on university campuses, demonstrating its effectiveness. FedKit is open-source at https://github.com/FedCampus/FedKit.

Beilong Tang, Bang Zeng, Ming Li

We propose LauraTSE, an Auto-Regressive Decoder-Only Language Model for Target Speaker Extraction built upon the LauraGPT backbone. LauraTSE employs a small-scale auto-regressive decoder-only language model that generates the initial layers of the target speech's discrete codec representations from the continuous embeddings of both the mixture and reference speech. These outputs serve as coarse-grained predictions. To refine them, a one-step encoder-only language model reconstructs the full codec representation by integrating information from both the mixture and the reference speech, adding fine-grained details. Experimental results show that our approach can achieve promising performance. Additionally, we conduct ablation studies to investigate the data scalability and the contribution of the encoder-only model.

Beilong Tang, Xiaoxiao Miao, Xin Wang et al.

Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a novel speaker-embedding-free framework called SEF-MK. Instead of using a single k-means model trained on the entire dataset, SEF-MK anonymizes SSL representations for each utterance by randomly selecting one of multiple k-means models, each trained on a different subset of speakers. We explore this approach from both attacker and user perspectives. Extensive experiments show that, compared to a single k-means model, SEF-MK with multiple k-means models better preserves linguistic and emotional content from the user's viewpoint. However, from the attacker's perspective, utilizing multiple k-means models boosts the effectiveness of privacy attacks. These insights can aid users in designing voice anonymization systems to mitigate attacker threats.