A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech Systems: Revealing Gaps in Syntactic Sensitivity

TL;DR

This paper investigates how well Text-to-Speech systems use syntactic cues to generate natural intonational phrasing, revealing limitations in handling ambiguous structures and proposing finetuning to improve sensitivity.

Contribution

It introduces a psycholinguistically inspired analysis of TTS intonational phrasing and demonstrates that finetuning enhances the systems' sensitivity to subtle syntactic cues.

Findings

TTS systems struggle with ambiguous syntactic boundaries.

Superficial cues like commas influence boundary placement.

Finetuning improves the reflection of syntactic structure in intonation.

Abstract

We analyze the syntactic sensitivity of Text-to-Speech (TTS) systems using methods inspired by psycholinguistic research. Specifically, we focus on the generation of intonational phrase boundaries, which can often be predicted by identifying syntactic boundaries within a sentence. We find that TTS systems struggle to accurately generate intonational phrase boundaries in sentences where syntactic boundaries are ambiguous (e.g., garden path sentences or sentences with attachment ambiguity). In these cases, systems need superficial cues such as commas to place boundaries at the correct positions. In contrast, for sentences with simpler syntactic structures, we find that systems do incorporate syntactic cues beyond surface markers. Finally, we finetune models on sentences without commas at the syntactic boundary positions, encouraging them to focus on more subtle linguistic cues. Our findings indicate that this leads to more distinct intonation patterns that better reflect the underlying structure.