Deep learning has been the mainstream technique in natural language processing (NLP)
area. However, the techniques require many labeled data and are less generalizable across …

Recent research shows a big convergence in model architecture, training objectives, and
inference methods across various tasks for different modalities. In this paper, we propose …

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural
language processing models, we propose a unified-modal SpeechT5 framework that …

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance
on various natural language processing tasks, and have shown great potential as …

Large language models (LLMs) have shown incredible proficiency in performing tasks that
require semantic understanding of natural language instructions. Recently, many works …

Large language models (LLMs) have gained considerable attention for Artificial Intelligence
Generated Content (AIGC), particularly with the emergence of ChatGPT. However, the direct …

Self-supervised learning (SSL) for rich speech representations has achieved empirical
success in low-resource Automatic Speech Recognition (ASR) and other speech processing …

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance
on various natural language processing tasks. However, there has been limited research on …

We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It
supports both Chinese and English, engages in real-time voice conversations, and varies …

Speech representation learning plays a vital role in speech processing. Among them, self-
supervised learning (SSL) has become an important research direction. It has been shown …