A Comparison between HTK and SPHINX on Chinese Mandarin
| Autor: | Guangguang Ma, Weiping Ye, Xiaomei You, Jing Zheng, Wenli Zhou |
|---|---|
| Rok vydání: | 2009 |
| Předmět: |
Sphinx
business.industry Computer science Speech recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION computer.software_genre Mandarin Chinese language.human_language ComputingMethodologies_PATTERNRECOGNITION language Artificial intelligence Mel-frequency cepstrum business Hidden Markov model computer Natural language Natural language processing |
| Zdroj: | JCAI |
| Popis: | In order to show the performances between different speech recognition engines in Chinese Mandarin recognition, experiments are designed in this paper to compare the recognition performances on Chinese Mandarin between HTK and Sphinx, which are the two most popular open source automatic speech recognition systems. Both isolated words recognition and continuous sentences recognition were investigated. The effects of number of Gaussians and number of tied-states for each system were also shown in this paper. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|