面向印度语言的跨语言 TTS：基准与推理时时长估计策略

View PDF HTML (experimental)

Abstract:Recent alignment-free Text-to-Speech (TTS) models achieve high synthesis quality by removing explicit alignment modules and simplifying training. However, they often struggle in cross-lingual scenarios due to differences in character durations across languages, leading to duration mismatch and degraded speech quality. Existing approaches typically address this issue using explicit duration predictors, increasing model complexity. Systematic evaluation of TTS performance for Indian languages in cross-lingual settings remains under-explored due to the lack of standardized evaluation benchmarks. In this work, we construct a cross-lingual evaluation benchmark covering English and nine Indian languages and propose a language-aware inference-time duration estimation strategy for alignment-free TTS that incorporates language-specific duration-per character statistics without retraining or architectural modifications. We further develop heuristic formulations that refine duration estimation based on language-dependent duration variations. Experiments on bilingual and multilingual A-DMA models demonstrate improved speech naturalness, intelligibility, and speaker similarity while reducing duration mismatch.

Comments:	9 pages, 3 figures, 5 tables. Accepted at the AACL-IJCNLP 2026 Workshop Multi-LLL. The dataset and code recipes are available at: this https URL
Subjects:	Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Sound (cs.SD)
Cite as:	arXiv:2610.14826 [eess.AS]
	(or arXiv:2610.14826v1 [eess.AS] for this version)
	https://doi.org/10.48550/arXiv.2610.14826 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Adarsh Arigala [view email]
[v1] Sat, 10 Oct 2026 11:41:56 UTC (77 KB)