ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

Documenti analoghi

• Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization
  di: Thienpondt, Jenthe, et al.
  Pubblicazione: (2024)
• Weakly Supervised Phonological Features for Pathological Speech Analysis
  di: Thienpondt, Jenthe, et al.
  Pubblicazione: (2025)
• Harmonic Summation-Based Robust Pitch Estimation in Noisy and Reverberant Environments
  di: Singh, Anup, et al.
  Pubblicazione: (2025)
• Attention-Based Audio Embeddings for Query-by-Example
  di: Singh, Anup, et al.
  Pubblicazione: (2022)
• BEST-STD2.0: Balanced and Efficient Speech Tokenizer for Spoken Term Detection
  di: Singh, Anup, et al.
  Pubblicazione: (2025)