robot

FunAudioLLM: Foundation Models for Voice Understanding and Generation for Natural Interaction Between Humans and LLMs

At its core, it features two innovative models: SenseVoice for high-precision multi-language speech recognition, emotion recognition, and audio event detection; and CosyVoice for natural voice generation with multi-language, timbre, and emotion control. SenseVoice boasts extremely low latency and supports over 50 languages, while CosyVoice excels in multi-language voice generation, zero-shot voice generation, cross-language voice cloning, and the ability to follow instructions. By integrating these models with LLMs, FunAudioLLM enables applications such as voice translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thus pushing the boundaries of voice interaction technology.

article image

"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs" introduces a framework designed to enhance natural voice interaction between humans and large language models (LLMs).

  1. General Overview Core Models: It includes SenseVoice for high-precision multi-language speech recognition, emotion recognition, and audio event detection, as well as CosyVoice for natural voice generation with multi-language, timbre, and emotion control. Open Source Status: The models are open-sourced on Modelscope and Huggingface, with corresponding training, inference, and fine-tuning code released on GitHub.
  2. SenseVoice Model Functional Overview Multi-language Speech Recognition: Supports over 50 languages, and compared with Whisper on open-source benchmark datasets such as AISHELL-1 and AISHELL-2, SenseVoice-Small adopts a non-autoregressive end-to-end architecture with extremely low inference latency, being 7 times faster than Whisper-Small and 17 times faster than Whisper-Large. Voice Emotion Recognition: Supports recognition of emotions such as Happy, Sad, Angry, and Neutral, and evaluated on 7 popular emotion recognition datasets, SenseVoice-Large can approach or exceed SOTA results on most datasets without target corpus fine-tuning. Audio Event Detection: SenseVoice-Large can predict the start and end positions of audio events, while SenseVoice-Small can detect more events such as coughing, sneezing, etc. Model Architecture: Includes SenseVoice-Small (a fast voice understanding base model with only an encoder) and SenseVoice-Large (an encoder-decoder model that supports more languages for more accurate voice understanding).
  3. CosyVoice Model Functional Features Multi-language Voice Generation: Can generate voices in multiple languages. Zero-shot Context Generation: Generates content according to prompts in different languages. Style Control: Can control the style of the voice, such as pitch, speaking rate, emotions, etc. Emotion-expressive Voice Generation: Can generate voices with different emotions. Speaker Fine-tuning and Interpolation: Can fine-tune speakers and also perform speaker interpolation. Inference Overview: Voice tokens are generated by an autoregressive transformer, Mel spectrograms are reconstructed based on an ODE-based diffusion model and flow matching, and waveforms are synthesized by HiFTNet vocoder.
  4. FunAudioLLM Applications Voice Translation: Integrates SenseVoice, LLMs, and CosyVoice to achieve voice-to-voice translation. Emotional Voice Chat: Develops an emotional voice chat application by integrating the three components, with user and assistant content synthesized by CosyVoice. Interactive Podcasts: Creates interactive podcasts by combining related components. Audiobooks: Utilizes the analytical capabilities of LLMs and the expressive synthesis of CosyVoice to create more expressive audiobooks.