Skip to content

Minje Kim's Home

Minje Kim's Home Minje Kim's Home

Innovation and Education in AI and Audio Processing

  • Home
  • News
  • Team
  • Research Projects
    • Personalized Speech Enhancement
      • Collaborative Deep Learning
      • Sparse Mixture of Local Experts
      • Knowledge Distillation for PSE
      • Self-Supervised Learning and Data Purification for PSE
      • TGIF: A Family-Owned Voice AI
    • Music Applications
      • Neural Pitch Correction of Singing Voice
      • SpaIn-Net: Spatially Informed Music Source Separation
      • Don’t Separate, Learn to Remix: End-to-End Neural Remixing
      • Neural Upmixing via Style Transfer
    • Neural Speech and Audio Coding
      • Audio Coding for Machines
      • LaDiffCodec: Generative De-Quantization for Neural Speech Codec via Latent Diffusion
      • Personalized Neural Speech Codec
      • From Hallucination to Articulation: Language Model-Driven Losses for Neural Speech Coding
      • Psychoacoustic Loss Functions for Neural Audio Coding
      • Cross-Module Residual Learning for Neural Audio Coding
      • Source-Aware Neural Audio Coding
    • Learning to Hash for Source Separation
    • Collaborative Audio Enhancement
    • Scalable and Efficient AI
      • BLOOM-Net: Scalability Matters
      • Scalable and Efficient Speech Enhancement Using Modified Cold Diffusion
  • Publication
  • Blog
  • Prospective Students
CV

Neural Feature Predictor and Discriminative Residual Coding

Paper

Haici Yang, Wootaek Lim, and Minje Kim, “Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2023 [arXiv] (under review)

Source codes

https://github.com/haiciyang/Feature-predictor-for-speech-codec

Audio examples

genc_samples-1Download

Search

Follow Me

  • LinkedIn
  • Google
  • YouTube
  • X
  • Bluesky
Scroll to Top

Table of Contents

×
  • Paper
  • Source codes
  • Audio examples
→ Index