第二十七章 语音合成

来自cslt Wiki
跳转至: 导航搜索

教学资料

扩展阅读

  • AI100问:甜美的导航声音是如何产生的? [2]
  • 维基百科:语音合成 [3][4]
  • 维基百科:声码器 [5][6]

视频展示

  • 源-滤波器模型 [7]
  • Vocoder 1939 (long) [8]
  • Vocoder 1939 (short) [9]
  • Vocal folder [10]
  • Vocal tract [11]
  • Auditory perception [12]

演示链接

  • Tacotron2 [13]
  • CycleFlow 语音转换 [14]
  • Online demo for TTS and Voice conversion [15]
  • Online TTS demo [16]
  • IBM TTS demo [17]

开发者资源

  • CodePen Web demo for TTS [18]
  • Simple HTML code [19]
  • NVIDIA Tacotron2 [20]


高级读者

  • 汤志远,李蓝天,王东,石颖,蔡云麒,郑方,《语音识别基本法》,清华大学出牌社,2021. [21]
  • Dudley H. The vocoder—Electrical re-creation of speech[J]. Journal of the Society of Motion Picture Engineers, 1940, 34(3): 272-278. [22]
  • Dudley H. Remaking speech[J]. The Journal of the Acoustical Society of America, 1939, 11(2): 169-177.[23]
  • Dudley, Homer (October 1940). "The Carrier Nature of Speech". Bell System Technical Journal. XIX (4). [24]
  • Ning Y, He S, Wu Z, et al. A review of deep learning based speech synthesis[J]. Applied Sciences, 2019, 9(19): 4050. [25][26]
  • Zen H, Tokuda K, Black A W. Statistical parametric speech synthesis[J]. speech communication, 2009, 51(11): 1039-1064. [27]