Improving Emotional TTS with an Emotion Intensity Input from Unsupervised Extraction

By Bastian Schnell, Philip N. Garner. 2021

14 citations recorded by the source corpus.

We aim to provide controls for emotion in synthetic speech. Many emotions are not displayed continuously in an otherwise emotional utterance; rather, the intensity varies with time. We show that an emotion recogniser is capable of producing a measure of emotion intensity via attention or saliency; this measure is appropriate to label utterances subsequently used to train a speech synthesiser. We evaluate novel and published means to do this showing that, whilst it is no longer state of the art for emotion recognition, attention is a good way to indicate emotion intensity for speech synthesis

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data (2024, background): “Cars displayed in these showrooms with ENERGY-EFFICIENT AND GREEN decals prominently featured across the windshield aren’t announcing environmentalism; they’re virtue signaling.”
An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era (2022, methodology): “…supported by SPSS vocoders, such as WORLD or STRAIGHT, which included F0, spectral/cepstral, and aperiodicity features [108], [110], [117], [121], [124], while works that only intended to use EVC as a means to improve SER performance [115] manipulated feature vectors used by the downstream models…”