arXiv (All)
open access
Asymmetric Classifier-Free Guidance for Target-Speaker ASR
Target-speaker automatic speech recognition (TS-ASR) must identify and transcribe a desired speaker under varying overlap and noise conditions. These changes alter the acoustic evidence for the target speaker in the speech mixture, motivating inference-time calibration of speaker conditioning. We in
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
- Inference-Time Target Speaker Unlearning in LLM-Based Automatic Speech Recognition#1104638
- BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation#1036287
- SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs#1084345
- Selective Attention System (SAS): Device-Addressed Speech Detection for Real-Time On-Device Voice AI#2648
- Probing Speaker Identity Sensitivity in Audio Deepfake Detectors#984202
Record · ID 1104675
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