GigaChat Audio: Time-aware Large Audio Language Model

Jul 14, 2026

Researchers introduce a time-aware audio large language model (LLM) capable of answering questions with explicit timestamps over audio inputs up to 120 minutes long. The model interleaves periodic time markers with continuous audio tokens, trained using large-scale synthetic supervision. It demonstrates strong temporal-grounding accuracy on both short and long audio benchmarks and supports time-anchored fragment descriptions and summaries.

Why it matters: This work enables precise temporal grounding in long audio recordings, advancing applications such as meeting analysis and media indexing.

Full story at: arXiv Audio and Speech Processing ↗