AI Chat AI Image Generator AI Video Text to Speech

Read it to me: An emotionally aware Speech Narration Application

09/06/2022

∙

by Rishibha Bansal, et al.

∙

∙

In this work we try to perform emotional style transfer on audios. In particular, MelGAN-VC architecture is explored for various emotion-pair transfers. The generated audio is then classified using an LSTM-based emotion classifier for audio. We find that "sad" audio is generated well as compared to "happy" or "anger" as people have similar expressions of sadness.

page 2

page 4

research

∙ 12/18/2018

Autoencoder Based Architecture For Fast & Real Time Audio Style Transfer

Recently, there has been great interest in the field of audio style tran...

0 Dhruv Ramani, et al. ∙

research

∙ 03/01/2023

READ Avatars: Realistic Emotion-controllable Audio Driven Avatars

We present READ Avatars, a 3D-based approach for generating 2D avatars t...

0 Jack Saunders, et al. ∙

research

∙ 05/15/2020

Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline

We propose the task of emotion style transfer, which is particularly cha...

0 David Helbig, et al. ∙

research

∙ 06/25/2022

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms

We describe our approach for the generative emotional vocal burst task (...

0 Marco Jiralerspong, et al. ∙

research

∙ 11/16/2022

Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition

Currently, the performance of Speech Emotion Recognition (SER) systems i...

0 Leyuan Qu, et al. ∙

research

∙ 03/30/2018

Automatically augmenting an emotion dataset improves classification using audio

In this work, we tackle a problem of speech emotion classification. One ...

0 Egor Lakomkin, et al. ∙

research

∙ 04/19/2023

Affective social anthropomorphic intelligent system

Human conversational styles are measured by the sense of humor, personal...

0 Md. Adyelullahil Mamun, et al. ∙