Senior Researcher, Speech Synthesis and Multimodal LLM｜高级研究员 - 语音合成与多模态大模型
Core
Research and develop advanced speech synthesis and generation algorithms (e.g., TTS, voice conversion, sound/music generation) based on LLMs and multimodal/omnimodal LLMs for online applications.
Role type
Senior Researcher, Speech Synthesis and Multimodal LLM
Builds
Speech synthesis systems, audio generation models, and real-time spoken interaction capabilities for games and online applications.
Domain
Gaming, Speech/Audio Processing, Generative AI
Deliverable
production ML models
Required skills
LLMs, speech/audio processing, diffusion models, flow matching, autoregressive models, codec-based approaches, speech tokenizers, multimodal adapters, speech-text joint training, Python, PyTorch, distributed training, top-tier academic publications
Preferred skills
full-duplex systems, streaming spoken dialogue systems, real-time interaction modeling
Technologies
PyTorch, LLMs, diffusion, flow matching, autoregressive models, codecs
Responsibilities
Research and develop speech synthesis and generation algorithms; Optimize speech and audio synthesis systems for online applications; Explore full-duplex/streaming multimodal LLM capabilities; Collaborate cross-functionally from prototyping to production.