SDCLLGASNov 29, 2022

Controllable speech synthesis by learning discrete phoneme-level prosodic representations

arXiv:2211.16307v110 citationsh-index: 20
Originality Incremental advance
AI Analysis

This work addresses the challenge of intuitive prosody control in text-to-speech systems for applications requiring natural and expressive speech synthesis, representing an incremental improvement with specific gains.

The paper tackles the problem of fine-grained phoneme-level prosody control in speech synthesis by proposing an unsupervised method to learn discrete prosodic representations, enabling control over F0 and duration without reference audio while maintaining speaker identity and high output quality.

In this paper, we present a novel method for phoneme-level prosody control of F0 and duration using intuitive discrete labels. We propose an unsupervised prosodic clustering process which is used to discretize phoneme-level F0 and duration features from a multispeaker speech dataset. These features are fed as an input sequence of prosodic labels to a prosody encoder module which augments an autoregressive attention-based text-to-speech model. We utilize various methods in order to improve prosodic control range and coverage, such as augmentation, F0 normalization, balanced clustering for duration and speaker-independent clustering. The final model enables fine-grained phoneme-level prosody control for all speakers contained in the training set, while maintaining the speaker identity. Instead of relying on reference utterances for inference, we introduce a prior prosody encoder which learns the style of each speaker and enables speech synthesis without the requirement of reference audio. We also fine-tune the multispeaker model to unseen speakers with limited amounts of data, as a realistic application scenario and show that the prosody control capabilities are maintained, verifying that the speaker-independent prosodic clustering is effective. Experimental results show that the model has high output speech quality and that the proposed method allows efficient prosody control within each speaker's range despite the variability that a multispeaker setting introduces.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes