Titlebook: Man-Machine Speech Communication; 14th National Confer Jianhua Tao,Thomas Fang Zheng,Ya Li Conference proceedings 2018 Springer Nature Sing

過去分詞

Emotion Recognition Using Support Vector Machine and Deep Neural Network,dentify the emotions for each utterance. The experimental results show that all the subsystems outperform the hidden markov model (HMM) baseline, and the combined system get the best performance on F-score.

情愛

Distance-Dependent Modeling of Head-Related Transfer Functions Based on Spherical Fourier-Bessel Trtation for HRTFs over the whole space. As a result, it is feasible to interpolate or extrapolate an HRTF on an unmeasured position. The experimental results show that DSHM achieves a lower LSD when comparing with the conventional SH-based method.

Electrolysis

聚集

peptic-ulcer

GRILL

Using Mandarin Training Corpus to Realize a Mandarin-Tibetan Cross-Lingual Emotional Speech Syntheshow that the method can synthesize both emotional Mandarin speech and emotional Tibetan speech with high naturalness and emotional similarity. Therefore, the method can be adopted to realizing an emotional speech synthesis with exiting emotional training corpus for languages lacking emotional speech resources.

持續(xù)

Uyghur Word Stemming Based on Stem and Affix Features,ffix-occurred probability feature, which provided the stemming accuracy of 88.59% for a baseline system. The performance of this stemmer was further improved by using parameter ‘α’ in combination with the proposed method.

Coronation

myocardium

Rinne-Test

Perception of English Phonemes by Chinese College Students,er and more accurately than consonants, which may be caused by sudden decrease/increase or “zero point” in frequency of consonants, or a larger acoustic power of vowels. Although no significant perception difference between high-frequency words (HFW) and low-frequency words (LFW) was found for all t