This research paper introduces CosyVoice 2, an improved streaming speech synthesis model. Building upon its predecessor, CosyVoice 2 utilizes advancements in large language models (LLMs) and incorporates optimizations like finite scalar quantization and a chunk-aware causal flow matching model. The result is a system achieving near human-parity naturalness with minimal latency in streaming mode, supporting multiple languages and offering fine-grained control over speech characteristics. The paper details the model's architecture, training data, and experimental results, demonstrating its superior performance compared to existing models. Limitations and future research directions are also discussed.
ai , artificial intelligence , arxiv , research , paper , publication , llm, genai, generative ai , large visual models, large language models, large multi modal models, nlp, text, machine learning, ml, nividia, openai, anthropic, microsoft, google, technology, cutting-edge, meta, llama, chatgpt, gpt, elon musk, sam altman, deployment, engineering, scholar, science, apple, samsung, anthropic, turing
