Tone Recognition Using MLP and Prosody Model
碩士 === 國立交通大學 === 電信工程系所 === 95 === In this thesis, the features of the preceding and the succeeding syllable are used to help tone recognition on MLP (multi-layer perceptron) tone recognizer. The features include means and slopes of three uniformly divided-pitch contour, duration of the syllable an...
Main Author: | 陳宏宇 |
---|---|
Other Authors: | 陳信宏 |
Format: | Others |
Language: | zh-TW |
Published: |
2007
|
Online Access: | http://ndltd.ncl.edu.tw/handle/zv8mev |
Similar Items
-
Prosody and Tone Modeling for Mandarin Chinese with Applications in Speech Recognition and Prosody Prediction
by: Li-Wei Cheng, et al.
Published: (2008) -
The prosody of Swedish underived nouns: No lexical tones required
by: Bruce Morén-Duolljá
Published: (2013-02-01) -
Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information
by: Medine Colak, et al.
Published: (2020-02-01) -
The use of prosody in speech recognition systems
by: De Backer, Philippe Paul
Published: (2007) -
A prosody-theoretic approach to Southem Min special tone sandhi
by: Ou, Shu Zhen, et al.
Published: (1996)