Zoe Xu

Jing Xu, Daxin Tan, Jiaqi Wang et al.

While Large Language Models (LLMs) have shown potential in speech generation and recognition, their applications are mainly confined to monolingual scenarios, with limited explorations in code-switched (CS) contexts. In this paper, we propose a Code-Switched Large Language Model (CS-LLM) to enhance the code-switched text-to-speech synthesis (CS TTS) capability in LLMs with only monolingual corpora. Specifically, we begin by enhancing the multilingual speech processing ability of LLMs through multilingual speech recognition and synthesis tasks. Then, we develop an effective code-switched (CS) data construction strategy that splits and concatenates words from different monolingual speech corpora to equip LLMs with improved CS TTS ability. Experiments show that our approach outperforms baselines in CS TTS in terms of naturalness, speaker consistency and similarity even with limited data. Additionally, the constructed CS data further improves multilingual speech synthesis and recognition.

Yifei Deng, Chenglong Li, Zhenyu Chen et al.

The performance of traditional text-image person retrieval task is easily affected by lighting variations due to imaging limitations of visible spectrum sensors. In recent years, cross-modal information fusion has emerged as an effective strategy to enhance retrieval robustness. By integrating complementary information from different spectral modalities, it becomes possible to achieve more stable person recognition and matching under complex real-world conditions. Motivated by this, we introduce a novel task: Text-RGBT Person Retrieval, which incorporates cross-spectrum information fusion by combining the complementary cues from visible and thermal modalities for robust person retrieval in challenging environments. The key challenge of Text-RGBT person retrieval lies in aligning text with multi-modal visual features. However, the inherent heterogeneity between visible and thermal modalities may interfere with the alignment between vision and language. To handle this problem, we propose a Decoupled Cross-modal Alignment network (DCAlign), which sufficiently mines the relationships between modality-specific and modality-collaborative visual with the text, for Text-RGBT person retrieval. To promote the research and development of this field, we create a high-quality Text-RGBT person retrieval dataset, RGBT-PEDES. RGBT-PEDES contains 1,822 identities from different age groups and genders with 4,723 pairs of calibrated RGB and T images, and covers high-diverse scenes from both daytime and nighttime with a various of challenges such as occlusion, weak alignment and adverse lighting conditions. Additionally, we carefully annotate 7,987 fine-grained textual descriptions for all RGBT person image pairs. Extensive experiments on RGBT-PEDES demonstrate that our method outperforms existing text-image person retrieval methods.