DPP-TTS: Diversifying prosodic features of speech via determinantal point processes

Published: 07 Oct 2023, Last Modified: 01 Dec 2023EMNLP 2023 MainEveryoneRevisionsBibTeX
Submission Type: Regular Long Paper
Submission Track: Speech and Multimodality
Submission Track 2: Phonology, Morphology, and Word Segmentation
Keywords: Speech prosody; prosodic segmentation; text-to-speech
TL;DR: We propose DPP-TTS, a text-to-speech model that boosts the diveristy of speech prosody.
Abstract: With the rapid advancement in deep generative models, recent neural Text-To-Speech(TTS) models have succeeded in synthesizing human-like speech. There have been some efforts to generate speech with various prosody beyond monotonous prosody patterns. However, previous works have several limitations. First, typical TTS models depend on the scaled sampling temperature for boosting the diversity of prosody. Speech samples generated at high sampling temperatures often lack perceptual prosodic diversity, which can adversely affect the naturalness of the speech. Second, the diversity among samples is neglected since the sampling procedure often focuses on a single speech sample rather than multiple ones. In this paper, we propose DPP-TTS: a text-to-speech model based on Determinantal Point Processes (DPPs) with a prosody diversifying module. Our TTS model is capable of generating speech samples that simultaneously consider perceptual diversity in each sample and among multiple samples. We demonstrate that DPP-TTS generates speech samples with more diversified prosody than baselines in the side-by-side comparison test considering the naturalness of speech at the same time.
Submission Number: 474
Loading