Phone-Dependent channel compensated hidden Markov model for telephone speech recognition

Jen-Tzung Chien*, Hsiao Chuan Wang

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

In this letter, we propose the phone-dependent channel compensated hidden Markov model (PDCC-HMM) for telephone speech recognition. The PDCC-HMM is derived by modifying the conventional hidden Markov model (HMM) with the phone-dependent channel compensation vectors. The telephone speech is recognized efficiently by using the derived PDCC-HMM. Experiments demonstrate the robustness of PDCC-HMM in speech recognition and show the significant reduction of recognition error rate by 50% as comparing to the conventional HMM method.

Original languageEnglish
Pages (from-to)143-145
Number of pages3
JournalIEEE Signal Processing Letters
Volume5
Issue number6
DOIs
StatePublished - 1 Dec 1998

Fingerprint Dive into the research topics of 'Phone-Dependent channel compensated hidden Markov model for telephone speech recognition'. Together they form a unique fingerprint.

Cite this