pith. sign in

Neil Zeghidour

Identifiers

  • name variant Neil Zeghidour 0.60 · backfill

Papers (15)

  1. MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models cs.CL · 2026 · author #4
  2. Adaptive Test-Time Scaling for Zero-Shot Respiratory Audio Classification cs.SD · 2026 · author #4
  3. Language Models as Semantic Teachers: Post-Training Alignment for Medical Audio Understanding cs.SD · 2025 · author #3
  4. Moshi: a speech-text foundation model for real-time dialogue eess.AS · 2024 · author #8
  5. AudioPaLM: A Large Language Model That Can Speak and Listen cs.CL · 2023 · author #26
  6. MusicLM: Generating Music From Text cs.SD · 2023 · author #12
  7. Deep multi-class learning from label proportions cs.LG · 2019 · author #2
  8. Fully Convolutional Speech Recognition cs.CL · 2018 · author #1
  9. To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition cs.LG · 2018 · author #2
  10. Learning to detect dysarthria from raw speech cs.CL · 2018 · author #2
  11. End-to-End Speech Recognition From the Raw Waveform cs.CL · 2018 · author #1
  12. Sampling strategies in Siamese Networks for unsupervised speech representation learning cs.CL · 2018 · author #4
  13. Learning Filterbanks from Raw Speech for Phone Recognition cs.CL · 2017 · author #1
  14. Fader Networks: Manipulating Images by Sliding Attributes cs.CV · 2017 · author #2
  15. Learning weakly supervised multimodal phoneme embeddings cs.CL · 2017 · author #3

Mentions

  • 2306.12925 #26 · arxiv_oai · confidence 0.70 Neil Zeghidour

Frequent Coauthors