Abstract Compression of Conversational Audio Context for LLM-based ASR
| Type of publication: | Conference paper |
| Citation: | Kumar_SLT2026-2_2026 |
| Publication status: | Accepted |
| Booktitle: | IEEE Spoken Language Technology 2026 |
| Year: | 2026 |
| URL: | https://arxiv.org/abs/2603.262... |
| Abstract: | Standard LLM-based speech recognition systems process utterances in isolation, limiting their ability to leverage conversational context. Here we study whether multimodal context from prior turns improves LLM-based ASR and how to represent that context efficiently. We find that, after supervised multi-turn training, conversational context mainly helps with the recognition of contextual entities. However, conditioning on raw context is expensive because the prior-turn audio embedding sequence grows rapidly with conversation length. To address this, we propose Abstract Compression, a learned latent abstraction of prior-turn audio that replaces each prior-turn audio sequence with a fixed number of latent tokens while retaining corresponding transcripts explicitly. On both in-domain and out-of-domain test sets, the compression-enabled model recovers part of the gains of raw-context conditioning with a smaller prior-turn audio footprint. We also provide targeted analyses of the compression setup and its tradeoffs. |
| Main Research Program: | AI for Everyone |
| Additional Research Programs: |
AI for Life |
| Keywords: | |
| Projects: |
UNIPHORE ELOQUENCE |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
