Classic Speech Processing Readings

  1. Tree-Based State Tying for High Accuracy Modelling
  2. The Application of Hidden Markov Models in Speech Recognition
  3. ABX evaluations I and II
  4. RASTA features from Hermansky
  5. CTC loss to label unsegmented sequences
  6. Weighted finite-state transducers in speech recognition
  7. A Robust algorithm for pitch tracking RAPT
  8. Temporal information in speech: acoustic, auditory and linguistic aspects link
  9. A recursive algorithm for the forced alignment of very long audio segments
  10. Temporal information in speech: acoustic, auditory and linguistic aspects link
  11. Meaning of the Hilbert Transform obtained from the analytic signal link and link

Classic Machine Listening Readings

  1. Auditory grouping
  2. Prediction-driven computational auditory scene analysis PhD thesis from Dan Ellis
  3. Audition chapter
  4. Modulation power spectrum series from Shamma’s group I II III