Papers › SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval

SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval

16 Dec 2024arXiv:2412.12009archive 2025-07-28

Yueqian Lin, Yuzhe Fu, Jingyang Zhang, Yudong Liu, Jianyi Zhang, Jingwei Sun, Hai "Helen" Li, Yiran Chen

We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately 90-second spoken inputs. While current Speech LLMs excel at short-form tasks, they struggle with the computational and representational demands of longer audio sequences. To address this limitation, we propose SpeechPrune, a training-free token pruning strategy that uses speech-text similarity and approximated attention scores to efficiently discard irrelevant tokens. In SPIRAL, SpeechPrune achieves accuracy improvements of 29% and up to 47% over the original model and the random pruning model at a pruning rate of 20%, respectively. SpeechPrune can maintain network performance even at a pruning level of 80%. This approach highlights the potential of token-level pruning for efficient and scalable long-form speech understanding.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

linyueqian/spiral_dataset officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

FormInformation RetrievalRetrievaltext similarity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionPruningSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections