提出并实现了一种基于广义人工神经网络和STRAIGHT模型的高效基频轨迹跟踪算法。
This paper proposes an efficient morphing algorithm of pitch based on generalized artificial intelligence and the STRAIGHT model.
各个音节的基频是随时间而变化的,其不同轨迹构成了声调,利用基频信息进一步提高了对汉语连续数字串的识别率。
In Chinese the pitch of syllable varies with time, whose track forms different tones. By using the pitch information the error rate of Mandarin connected digits is further decreased.
各个音节的基频是随时间而变化的,其不同轨迹构成了声调,利用基频信息进一步提高了对汉语连续数字串的识别率。
In Chinese the pitch of syllable varies with time, whose track forms different tones. By using the pitch information the error rate of Mandarin connected digits is further decreased.
应用推荐