Audio Synthesis Research Scientist, Speech and Audio

**About ByteDance**

Founded in 2012, ByteDance's mission is to inspire creativity and enrich life. With a suite of more than a dozen products, including TikTok, Helo, and Resso, as well as platforms specific to the China market, including Toutiao, Douyin, and Xigua, ByteDance has made it easier and more fun for people to connect with, consume, and create content.

**Why Join Us**

Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. To us, every challenge, no matter how ambiguous, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. Join us.

**About The Team**

Speech & Audio (SA) team provides industry-leading ML algorithm capabilities and complete voice product solutions for all business lines, including B2B as well. We empower businesses in the fields of speech/song synthesis, audio understanding, ML education, etc., and solve basic problems such as audio and video content understanding and creation, and human-computer voice interaction. The research team of audio generation group is committed to promoting the cutting-edge development of generative models in the fields of speech and virtual human, following up the leading research work in the academic industry, improving the academic influence and building technical barriers of SA team in related fields.

**Responsibilities**
- Basic generative models
- High-quality and expressive text-to-speech models
- Speech-driven talking face generation and human pose generation
- Speech-to-speech translation and simultaneous translation
- Singing voice synthesis
- Audio generation conditioned on text, image and video
- Support the production of scalable and optimised AI/machine learning (ML) models
- Focus on building algorithms for the extraction, transformation and loading of large volumes of Realtime, unstructured data to deploy AI/ML solutions from theoretical data science models
- Run experiments to test the performance of deployed models, and identifies and resolves bugs that arise in the process
- Work with the relevant software platforms in which the models are deployed

**Qualifications**
- Ph.D student or Master student by research from top universities, majoring in EE or CS in the related areas (CV/NLP/Speech). Speech-related background is optional
- Having publications/submissions in relevant conferences/journals
- Familiar with the recent advance in the field of deep learning and generative models
- Self-driven, innovative, collaborative, with good communication and presentation skills
- Proficiency in one or more of the community open source tools such as Pytorch, Tensorflow, Jax

**Preferred Qualifications**
- Having publications/submissions in top-tier conferences/journals (e.g., ICML、ICLR、NeurIPS、CVPR、ICCV and TPAMI), or winning the best paper award/best paper nomination/other honors in relevant international conferences/journals

ByteDance is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At ByteDance, our mission is to inspire creativity and enrich life. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.