GigaChat Audio: Time-aware Large Audio Language Model

• URL: http://arxiv.org/abs/2607.10387v1
• Date: Sat, 11 Jul 2026 16:34:25 GMT
• Title: GigaChat Audio: Time-aware Large Audio Language Model
• Abstract summary: We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input.<n>Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline.
• Score: 65.51589021112385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture design affect accuracy and computational cost. We release model weights and datasets to support further research on time-aware audio understanding, available at https://huggingface.co/ai-sage/GigaChat3.1-Audio-10B-A1.8B.

Related papers

• TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models [58.80225070159013]
  Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify.<n>We present TEMPO, the first unified model to handle audio, speech, and music timestamping tasks.
  arXiv  Detail & Related papers  (2026-08-30T19:49:21Z)
• MOSS-Audio Technical Report [80.01042232102883]
  MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding.<n>It supports audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning.
  arXiv  Detail & Related papers  (2026-06-01T07:19:22Z)
• Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models [56.91801348360746]
  Large audio-language models (LALMs) generalize across speech, sound, and music.<n> unified decoders can exhibit a emphtemporal smoothing bias<n>We propose emphTemporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs.
  arXiv  Detail & Related papers  (2026-04-16T02:30:41Z)
• Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt [26.402383197553778]
  We propose Audio-Side Time Prompt and leverage Reinforcement Learning to develop the TimePro-RL framework for fine-grained temporal perception.<n>Specifically, we encodes as embedding timestamps and interleave them within the audio feature sequence as temporal coordinates to prompt the model.<n>Experiments demonstrate that TimePro-RL achieves significant performance gains across a range of audio temporal tasks, such as audio grounding, sound event detection, and dense audio captioning.
  arXiv  Detail & Related papers  (2026-04-15T10:50:29Z)
• LongAudio-RAG: Event-Grounded Question Answering over Multi-Hour Long Audio [6.935416517354558]
  LongAudio Generation (LARAG) is a framework that grounds Large Language Model (LLM) outputs in retrieved, timestamped acoustic event detections.<n>We demonstrate the practicality of our approach by deploying it in a hybrid edge-cloud environment.<n>Experiments show that structured, event-level retrieval significantly improves accuracy compared to vanilla Retrieval-Augmentment.
  arXiv  Detail & Related papers  (2026-02-16T10:15:22Z)
• Frame-Level Internal Tool Use for Temporal Grounding in Audio LMs [48.50855715191533]
  Large audio language models are increasingly used for complex audio understanding tasks.<n>They struggle with temporal tasks that require precise temporal grounding, such as word alignment and speaker diarization.<n>We propose frame-level internal tool use, a method that trains audio LMs to use their own internal audio representations to perform temporal grounding directly.
  arXiv  Detail & Related papers  (2026-02-10T19:19:52Z)
• AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs [53.248502396225724]
  AudioMarathon is a benchmark designed to evaluate both understanding and inference efficiency on long-form audio.<n>We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows.<n>The results show large gaps across current LALMs and highlight the need for better temporal reasoning.
  arXiv  Detail & Related papers  (2025-10-08T17:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.