An overview of RNN-based mandarin speech recognition approaches

Yuan Fu Liao, Wei Tyng Hong, Wern Jun Wang, Yih-Ru Wang, Sin-Horng Chen*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

The ANN-based approach is an alternate to the HMM method which is the currently dominant technology in the field of speech recognition. This paper is an overview of the RNN-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. We find from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition.

Original languageEnglish
Pages (from-to)535-547
Number of pages13
JournalJournal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an
Volume22
Issue number5
DOIs
StatePublished - 1 Jan 1999

Keywords

  • HMM
  • Mandarin speech recognition
  • RNN

Fingerprint Dive into the research topics of 'An overview of RNN-based mandarin speech recognition approaches'. Together they form a unique fingerprint.

Cite this