HMM-based speech enhancement using harmonic modeling

Michael E. Deisher, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Scopus citations


This paper describes a technique for reduction of non-stationary noise in electronic voice communication systems. Removal of noise is needed in many such systems, particularly those deployed in harsh mobile or otherwise dynamic acoustic environments. The proposed method employs state-based statistical models of both speech and noise, and is thus capable of tracking variations in noise during sustained speech. This work extends the hidden Markov model (HMM) based minimum mean square error (MMSE) estimator to incorporate a ternary voicing state, and applies it to a harmonic representation of voiced speech. Noise reduction during voiced sounds is thereby improved. Performance is evaluated using speech and noise from standard databases. The extended algorithm is demonstrated to improve speech quality as measured by informal preference tests and objective measures, to preserve speech intelligibility as measured by informal Diagnostic Rhyme Tests, and to improve the performance of a low bit-rate speech coder and a speech recognition system when used as a pre-processor.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Editors Anon
Number of pages4
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger
Duration: Apr 21 1997Apr 24 1997


OtherProceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5)
CityMunich, Ger

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics


Dive into the research topics of 'HMM-based speech enhancement using harmonic modeling'. Together they form a unique fingerprint.

Cite this