An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion
This is an incremental review paper that synthesizes existing work to aid researchers in human-computer interaction and related fields.
The paper reviews sequence-to-sequence models for emotional voice conversion, which tackles the challenge of converting speech to different emotions by handling varying sequence lengths, and organizes recent research to provide an overview of the state-of-the-art.
Emotional voice conversion (EVC) focuses on converting a speech utterance from a source to a target emotion; it can thus be a key enabling technology for human-computer interaction applications and beyond. However, EVC remains an unsolved research problem with several challenges. In particular, as speech rate and rhythm are two key factors of emotional conversion, models have to generate output sequences of differing length. Sequence-to-sequence modelling is recently emerging as a competitive paradigm for models that can overcome those challenges. In an attempt to stimulate further research in this promising new direction, recent sequence-to-sequence EVC papers were systematically investigated and reviewed from six perspectives: their motivation, training strategies, model architectures, datasets, model inputs, and evaluation methods. This information is organised to provide the research community with an easily digestible overview of the current state-of-the-art. Finally, we discuss existing challenges of sequence-to-sequence EVC.