We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
於基礎聲學模型訓練階段,以長庚大學提供的台語語料 ForSD (Formosa Speech Database) [1] 為材料,使用隱藏式馬可夫模型(Hidden Markov Model, HMM)、梅爾倒 頻譜係數(Mel-frequency Cepstral Coefficients, MFCCs) [2] 和對數能量(Log energy) 做為語音特徵進行聲學模型的訓練。聲學模型單位分別為:單音素聲學模型(Monophone acoustic model)、音節內右相關雙連音素聲學模型(Biphone acoustic model)及音節內 左右相關三連音素聲學模型(Triphone acoustic model),其針對測試語料進行自由音節 解碼辨識網路(Free syllable(More)
This research focuses on validating a Taiwanese speech corpus by using speech recognition and assessment to automatically find the potentially problematic utterances. There are three main stages in this work: acoustic model training, speech assessment and error labeling, and performance evaluation. In the acoustic model training stage, we use the ForSD(More)
  • 1