arXiv (All)
open access
TS-OPD: Reconciling ASR and QA in Speech Language Models via Task-Specific On-Policy Distillation
Speech Language Models (SLMs) inherit strong instruction-following capabilities from pretrained language models, yet ASR specialization can substantially degrade them. To address this ASR--QA trade-off, we propose Task-Specific On-Policy Distillation (TS-OPD), which leverages models before and after
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- A Temporal-Envelope Frontend with Learnable Per-Channel Energy Normalization for Whisper-Based Children's ASR#1063148
- TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training#1118637
- Voice of Reason: Reinforcement Learning for Spoken Math#1012849
- BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding#1131064
- Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillation#1129925
Record · ID 1077393
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive