Soundgen: An open-source tool for synthesizing nonverbal vocalizations
Soundgen: An open-source tool for synthesizing nonverbal vocalizations
复制标题
DOI：
10.3758/s13428-018-1095-7
复制
发表时间：
2019-04-01
影响因子：
5.4
通讯作者：
Anikin, Andrey
中科院分区：
文献类型：
--
作者：
Anikin, Andrey
语音合成是研究不同声学特征的交流作用的有用方法。尽管有许多文本转语音系统可用，但人类非语言发声研究人员和生物声学家可能会受益于用于合成和操纵自然发声的专用简单工具。 Soundgen (https://CRAN.R-project.org/package=soundgen) 是一个开源 R 包，它根据有意义的声学参数合成非语言发声，这些参数可以从命令行或交互式应用程序中指定。通过比较 60 个录制的人类非语言发声（尖叫、呻吟、笑声等）的感知情绪、效价、唤醒度和真实性及其近似合成再现，验证了该工具。每个合成声音都是通过手动指定少量高级控制参数来创建的，例如音节长度和语调轮廓的一些锚点。尽管如此，合成声音的效价和唤醒评级与原始录音相似，真实性评级也具有可比性，与不太复杂的发声的原始声音保持一致。操纵合成声音的精确声学特征可能有助于揭示人类声音中情绪的显着预测因子。更一般地说，soundgen 可能对任何需要精确控制非语音声学特征的研究有用，包括动物发声和听觉感知的研究。
Voice synthesis is a useful method for investigating the communicative role of different acoustic features. Although many text-to-speech systems are available, researchers of human nonverbal vocalizations and bioacousticians may profit from a dedicated simple tool for synthesizing and manipulating natural-sounding vocalizations. Soundgen (https://CRAN.R-project.org/package=soundgen) is an open-source R package that synthesizes nonverbal vocalizations based on meaningful acoustic parameters, which can be specified from the command line or in an interactive app. This tool was validatedby comparing the perceived emotion, valence, arousal, and authenticity of 60 recorded human nonverbal vocalizations (screams, moans, laughs, and so on) and their approximate synthetic reproductions. Each synthetic sound was created by manually specifying only a small number of high-level control parameters, such as syllable length and a few anchors for the intonation contour. Nevertheless, the valence and arousal ratings of synthetic sounds were similar to those of the original recordings, and the authenticity ratings were comparable, maintaining parity with the originals for less complex vocalizations. Manipulating the precise acoustic characteristics of synthetic sounds may shed light on the salient predictors of emotion in the human voice. More generally, soundgen may prove useful for any studies that require precise control over the acoustic features of nonspeech sounds, including research on animal vocalizations and auditory perception.