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

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.

Proceedings of ICASSP 2021

References in corpus (5)

• MelNet: A Generative Model for Audio in the Frequency Domain
• CHiVE: Varying Prosody in Speech Synthesis with a Linguistically Driven Dynamic Hierarchical Conditional Variational Network
• High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency
• Semi-Supervised Generative Modeling for Controllable Speech Synthesis
• Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior

Cited by in corpus (4)

• Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
• Controllable speech synthesis by learning discrete phoneme-level prosodic representations
• Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control
• Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control