Rui Wang

Xinsheng Wang, Mingqi Jiang, Ziyang Ma et al.

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Yuanshuai Luo, Rui Wang, Yaxin Liang et al.

With the rapid growth of digital information, personalized recommendation systems have become an indispensable part of Internet services, especially in the fields of e-commerce, social media, and online entertainment. However, traditional collaborative filtering and content-based recommendation methods have limitations in dealing with data sparsity and cold start problems, especially in the face of largescale heterogeneous data, which makes it difficult to meet user expectations. This paper proposes a new label recommendation algorithm based on metric learning, which aims to overcome the challenges of traditional recommendation systems by learning effective distance or similarity metrics to capture the subtle differences between user preferences and item features. Experimental results show that the algorithm outperforms baseline methods including local response metric learning (LRML), collaborative metric learning (CML), and adaptive tensor factorization (ATF) based on adversarial learning on multiple evaluation metrics. In particular, it performs particularly well in the accuracy of the first few recommended items, while maintaining high robustness and maintaining high recommendation accuracy.