A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting

Documenti analoghi

• Cross-Domain Audio Deepfake Detection: Dataset and Analysis
  di: Li, Yuang, et al.
  Pubblicazione: (2024)
• UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction
  di: Guo, Jiaxin, et al.
  Pubblicazione: (2024)
• OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
  di: Sudo, Yui, et al.
  Pubblicazione: (2025)
• MATE: Matryoshka Audio-Text Embeddings for Open-Vocabulary Keyword Spotting
  di: Jung, Youngmoon, et al.
  Pubblicazione: (2026)
• WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing
  di: Nakagome, Yu, et al.
  Pubblicazione: (2025)