SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition

Documenti analoghi

• Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition
  di: Kocour, Martin, et al.
  Pubblicazione: (2025)
• On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
  di: Rossenbach, Nick, et al.
  Pubblicazione: (2024)
• Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities
  di: Adila, Aulia, et al.
  Pubblicazione: (2024)
• Gammatonegram Representation for End-to-End Dysarthric Speech Processing Tasks: Speech Recognition, Speaker Identification, and Intelligibility Assessment
  di: Farhadipour, Aref, et al.
  Pubblicazione: (2023)
• Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio
  di: He, Xinlu, et al.
  Pubblicazione: (2025)