CONF Schnell_SSW11_2021/IDIAP Improving Emotional TTS with an Emotion Intensity Input from Unsupervised Extraction Schnell, Bastian Garner, Philip N. Emotion Recognition emotional speech synthesis Saliency Mapping TTS EXTERNAL https://publications.idiap.ch/attachments/papers/2021/Schnell_SSW11_2021.pdf PUBLIC 11th ISCA Speech Synthesis Workshop 2021 https://www.idiap.ch/paper/ssw11_emotion_intensity/ URL 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.