Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis

TL;DR

This paper introduces a novel phoneme-level prosody control method in end-to-end speech synthesis by directly extracting and discretizing prosodic features, enabling detailed control over pitch and duration without sacrificing speech quality.

Contribution

It proposes a new approach that directly extracts and clusters prosodic features for phoneme-level control, bypassing traditional latent variable models.

Findings

Maintains high speech quality with phoneme-level prosody control.

Allows control over pitch, duration, and musical notes.

Enables manipulation of note and octave within speaker range.

Abstract

This paper presents a method for controlling the prosody at the phoneme level in an autoregressive attention-based text-to-speech system. Instead of learning latent prosodic features with a variational framework as is commonly done, we directly extract phoneme-level F0 and duration features from the speech data in the training set. Each prosodic feature is discretized using unsupervised clustering in order to produce a sequence of prosodic labels for each utterance. This sequence is used in parallel to the phoneme sequence in order to condition the decoder with the utilization of a prosodic encoder and a corresponding attention module. Experimental results show that the proposed method retains the high quality of generated speech, while allowing phoneme-level control of F0 and duration. By replacing the F0 cluster centroids with musical notes, the model can also provide control over the note and octave within the range of the speaker.