LabCompass

Haici Yang

Computer Science · Indiana University

OpenAlex
Speech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and SynthesisAdvanced Data Compression TechniquesAdvanced Vision and Imaging

Publications

26

Citations

127

Est. group size

—

Recurring co-author estimate

Active years

24

Publishing since 2002

Research summary
AI-generated

Haici Yang works on machine learning methods for processing speech and audio signals. Their research covers compressing speech efficiently (neural speech codecs), improving noisy or low-quality audio (speech enhancement), separating and remixing music sources, and detecting unusual audio patterns (anomaly detection). Much of this work uses modern generative models, such as diffusion models and discrete audio tokens, to reconstruct or transform sound.

Neural speech coding and compressionGenerative speech enhancementMusic source separation and remixingAudio anomaly detection and domain generalizationDiscrete audio tokens and representations

Publication activity has been steady over the past several years, averaging about three papers per year with a recent uptick in 2024 and 2025.

Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026

Publication cadence
Publications per year over the last 10 years — averaging 3.0/year recently
17182019: 1 publication192020: 6 publications6202021: 3 publications212022: 4 publications222023: 2 publications232024: 4 publications242025: 5 publications2526
Recent publications
Publishes in
  • arXiv (Cornell University)×9
  • ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)×2
  • PLoS ONE×1
  • IEEE Transactions on Audio Speech and Language Processing×1
  • Shuju fenxi yu zhishi faxian×1

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 11, 2026.

Claim or correct this profile