← authors · overview

• End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations
  2023 · 5 citations
• Extracting speaker and emotion information from self-supervised speech models via channel-wise correlations
  2022 · 1 citations
• Endpoint Anticipation for Low-Latency Spoken Dialogue
  2026
• Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning
  2026
• Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training
  2025
• How to Improve Your Speaker Embeddings Extractor in Generic Toolkits
  2018
• A Technical Report: BUT Speech Translation Systems
  2020
• BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge
  2021
• DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction
  2021
• An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification
  2022
• DiaCorrect: Error Correction Back-end For Speaker Diarization
  2023
• Target Speech Extraction with Pre-trained Self-supervised Learning Models
  2024
• Probing Self-supervised Learning Models with Target Speech Extraction
  2024