Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens
This enables multispeaker voice synthesis with style transfer and singing capabilities, addressing a need for more flexible and expressive text-to-speech systems without specialized training data.
The paper tackled the problem of generating expressive and singing voices without requiring emotive or singing training data, achieving this by conditioning on rhythm and pitch contours to produce a variety of speech styles, including rap and singing, using only read speech data.
Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning on rhythm and continuous pitch contours from an audio signal or music score, Mellotron is able to generate speech in a variety of styles ranging from read speech to expressive speech, from slow drawls to rap and from monotonous voice to singing voice. Unlike other methods, we train Mellotron using only read speech data without alignments between text and audio. We evaluate our models using the LJSpeech and LibriTTS datasets. We provide F0 Frame Errors and synthesized samples that include style transfer from other speakers, singers and styles not seen during training, procedural manipulation of rhythm and pitch and choir synthesis.