Job Overview:
As an Audio Algorithm Engineer based in Singapore, you will be at the forefront of audio technology and creative arts, pushing the boundaries of music and sound generation technology. You will design and implement advanced audio and machine learning models to enhance audio quality in products like Zoom Meeting, with key focus areas including Noise Suppression, Speaker Recognition, and Voice Activity Detection. Your work will involve creating models that understand, create, and optimize music and various sound effects, providing users with unprecedented personalized audio experiences. Additionally, you will stay informed about the latest research developments in audio technology to ensure our solutions remain cutting-edge. This role encompasses both audio research and software development.
Responsibilities:
- Collaborate with sound designers in building large audio models.
- Develop unimodal and multimodal models.
- Responsible for audio technology development, algorithm implementation, and optimization in audio and video products.
- Analyse and process large-scale audio materials.
- Maintain audio frontend quality algorithms to ensure product audio quality.
- Research and optimize large-scale audio generation models
- Explore and experiment with the latest research findings, converting them into practical product features such as automatic accompaniment generation and sound emotion simulation.
Requirements:
- Bachelor’s degree or higher in Computer Science, Signal Processing, Electronic Engineering, or related fields.
- Proficient in deep learning frameworks (such as TensorFlow, PyTorch) with experience in building complex audio generation models.
- In-depth understanding of audio signal processing, music theory, and acoustic principles.
- Ability to read and understand English scientific literature and stay highly informed on the latest research developments in audio technology.
- Deep understanding and practical experience in AIGC audio technology, SUNO, Stable Audio, particularly in audio generation and processing technologies, with a preference for those familiar with machine learning and deep learning algorithms.
- Extensive experience with Qwen Audio, and clear understanding of tasks related.
