CLMay 28, 2025

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

arXiv:2505.22236v21 citationsh-index: 18Proceedings of the 29th Conference on Computational Natural Language Learning
Originality Incremental advance
AI Analysis

This addresses a problem for TTS developers and linguists by revealing gaps in syntactic sensitivity, but it is incremental as it builds on existing psycholinguistic methods.

The paper analyzed the syntactic sensitivity of Text-to-Speech systems in generating intonational phrase boundaries, finding that systems struggle with ambiguous syntactic structures like garden path sentences and rely on superficial cues such as commas, but finetuning on sentences without commas improved intonation patterns to better reflect underlying structure.

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.

Foundations

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

Your Notes