Speech

ESD

Emotional Speech Database

Introduced in Emotional Voice Conversion: Theory, Databases and ESD2021

About this Dataset

ESD is an Emotional Speech Database for voice conversion research. The ESD database consists of 350 parallel utterances spoken by 10 native English and 10 native Chinese speakers and covers 5 emotion categories (neutral, happy, angry, sad and surprise). More than 29 hours of speech data were recorded in a controlled acoustic environment. The database is suitable for multi-speaker and cross-lingual emotional voice conversion studies.

Source: Emotional Voice Conversion: Theory, Databases and ESD

Dataset Variants

ESD

Papers1

Emotional Voice Conversion: Theory, Databases and ESD

The development of a novel emotional speech database (ESD) that addresses the increasing research need is motivated and the ESD database is now made available to the research community.

Dataset Loaders

EDIT

🔥

huggingface/parler-tts

tfpytorch

Tasks

EDIT

Voice Conversion

Similar Datasets