通过改变相应的语音参数可以灵活地调节音节的时长、基音频率和音强。
The duration and fundamental frequency can be changed by adjusted the speech parameters.
MFCC参数主要描述了表征声道特性的谱包络特征,而忽略了基音频率对它的影响。
MFCC parameters is main describes the spectrum envelope features, which is used to state the vacal track characterizatics, while ignoring the impact of pitch frequency.
通过修改基音频率和共振峰结构,该方法合成的语音有效地模拟了目标说话人的特性。
The modification of both pitch and formant structure contributed greatly to reproducing the target speaker's characteristics.
准确地进行基音频率的分析和提取一直是语音合成及语音识别等领域中所关注的核心问题之一。
The accurate pitch analysis and extraction is always one of the most key issue in speech synthesis and speech recognition.
针对语句后部的变调和基音频率的衰减,采用改进的自相关函数计算方法增强快变基音周期的跟踪。
We adopt improved computation of autocorrelation function for the case of fo change in the end of sentences, and realize accurate tracking to rapidly changed pitch.
该方法利用掌声与非掌声事件之间的时长和基音频率差异,无需构建复杂的统计模型就能检测出会议语音中的掌声。
The proposed approach can detect applause in meeting speech by only using the differences of duration and pitch between applause and non-applause events, without using any complex statistical models.
另外,本文就一种最常见的特征基音频率进行了一定的研究,并将之用于区分语音、音乐的系统中去,完成了一些实验。
In addition, we study pitch which is a common feature of audio, and use it to distinguish between speech and music.
分析了发音持续时间、平均振幅、基音频率,第一共振峰和Mel频率倒谱参数,并基于模糊熵理论提取了各参数的权重。
The improved method based on fuzzy entropy, which analyzed and distilled the weight of speech duration, average magnitudes, pitch frequency, formants and Mel-frequency cesptral coefficients.
本文结合语音信号中基音频率的频域特征及汉语语音的特点,利用小波分析技术,对汉语语音中韵母的基音频率等信息的提取进行了研究。
In this paper, taking account of the features of pitch and Chinese speech, we apply the Wavelet decomposition technique to analyse the pitch of Chinese speech.
本文结合语音信号中基音频率的频域特征及汉语语音的特点,利用小波分析技术,对汉语语音中韵母的基音频率等信息的提取进行了研究。
In this paper, taking account of the features of pitch and Chinese speech, we apply the Wavelet decomposition technique to analyse the pitch of Chinese speech.
应用推荐