GMM-based voice conversion applied to emotional speech synthesis

By Hiromichi Kawanami, Yohei Iwami, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano. 2003

101 citations recorded by the source corpus.

EUROSPEECH2003: 8th European Conference on Speech Communication and Technology, September 1-4, 2003, Geneva, Switzerland.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems (2018, methodology): “This would help in later work to maybe generate other emotions not present in our database in Russel’s model (using interpolation techniques for example [14]).”
Emotional voice conversion using deep neural networks with MCC and F0 features (2016, methodology): “We used a database of emotional Japanese speech constructed in [24].”
Emotional Voice Conversion: Theory, Databases and ESD (2021, methodology): “The early studies on emotional voice conversion include GMM technique (Aihara et al., 2012; Kawanami et al., 2003), sparse representation technique (Aihara et al.”
An overview of voice conversion systems (2017, background): “VT approaches can be applied to olve related problems, such as changing one emotion into another Kawanami et al., 2003 ), improving the intelligibility of speech Kain et al., 2007 ), or changing whisper/murmur into speech withut modifying speaker identity and linguistic content.”