arXiv (OAI Expanded)
open access
Quantifying the Generation Modality Gap in Speech-Text Language Models
Pure speech language models often lag behind text and speech-text language models in generating coherent content, but this gap is difficult to quantify because speech and text systems are typically evaluated with different metrics and trained on different data. We study the speech-text modality gap
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
- Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation#1109343
- Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure#1117767
- FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation#1064201
- Two temporally distinct prediction stages overlap under moderately faster speech#434918
- Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation#821201
Record · ID 1084668
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