CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations

• URL: http://arxiv.org/abs/2606.25403v1
• Date: Wed, 24 Jun 2026 05:02:36 GMT
• Title: CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
• Abstract summary: CrossAccentTTS is a framework that enables accent control and conversion while preserving speaker identity.<n>Experiments on the Indic Multilingual and L2-arctic datasets show that CrossAccent-TTS achieves precise control of accent intensity.
• Score: 9.312579603351827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-speech (TTS), particularly for low-resource and phonetically diverse Indic languages. While recent large language model (LLM)-based TTS systems exhibit strong cross-lingual generalization, they provide limited explicit control over accent characteristics and intensity. In this paper, we propose CrossAccentTTS, a framework that enables both accent control and conversion while preserving speaker identity. Specifically, we introduce an Accent Intensity Controller (AIC) that injects weighted language embeddings into the accent subspace, allowing smooth interpolation between accents and fine-grained modulation of accent strength at inference time. Experiments on the Indic Multilingual and L2-arctic datasets shows that CrossAccent-TTS achieves precise control of accent intensity, outperforming strong baselines in accent similarity and controllability by maintaining speaker similarity and naturalness.

Related papers

• KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026 [61.29502937013759]
  Cross-lingual voice cloning aims to generate speech in a target language while preserving speaker identity from a source-language reference.<n>Key challenge is maintaining intelligibility and naturalness in the presence of accent variation and domain-specific vocabulary.<n>We build on a multilingual text-to-speech model, FishAudio-S2-Pro, and introduce language tag prompting to improve language control and reduce accent leakage.
  arXiv  Detail & Related papers  (2026-06-05T13:09:21Z)
• Learning-free L2-Accented Speech Generation using Phonological Rules [46.06717601946553]
  We propose a accented text-to-speech framework that combines phonological rules with a multilingual TTS model.<n>The rules are applied to phoneme sequences to transform accent at the phoneme level while preserving intelligibility.<n>We design rule sets for Spanish- and Indian-accented English, modeling systematic differences in consonants, vowels, and syllable structure arising from phonotactic constraints.
  arXiv  Detail & Related papers  (2026-03-08T09:22:55Z)
• Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data [45.10765052993173]
  We propose textitAccent Vector, a controllable representation that enables accent manipulation in multilingual TTS.<n>textitAccent Vector is derived by fine-tuning a TTS system on native speech of a different language.<n>By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech.
  arXiv  Detail & Related papers  (2026-03-08T08:48:42Z)
• Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis [44.55147169458465]
  We analyze the interaction between speaker embeddings and linguistically motivated phonological rules in accented speech synthesis.<n>Experiments show that combining rules with embeddings yields more authentic accents.<n>Our findings highlight rules as a lever for accent control and a framework for evaluating disentanglement in speech generation.
  arXiv  Detail & Related papers  (2026-01-20T19:25:33Z)
• CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generation [15.730246391986002]
  Two biases persist in instruction-guided text-to-speech research: accent bias and linguistic bias.<n>We present Contextual Linguistic Adaptation and Retrieval for Inclusive TTS sYnthesis (CLARITY)<n>CLARITY is a backbone-agnostic framework that addresses these biases through dual-signal optimization.
  arXiv  Detail & Related papers  (2025-11-14T09:29:10Z)
• Accent conversion using discrete units with parallel data synthesized from controllable accented TTS [56.18382038512251]
  The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues.
  arXiv  Detail & Related papers  (2024-09-30T19:52:10Z)
• Explicit Intensity Control for Accented Text-to-speech [65.35831577398174]
  How to control the intensity of accent in the process of TTS is a very interesting research direction. Recent work design a speaker-versaadrial loss to disentangle the speaker and accent information, and then adjust the loss weight to control the accent intensity. This paper propose a new intuitive and explicit accent intensity control scheme for accented TTS.
  arXiv  Detail & Related papers  (2022-10-27T12:23:41Z)
• Controllable Accented Text-to-Speech Synthesis [76.80549143755242]
  We propose a neural TTS architecture that allows us to control the accent and its intensity during inference. This is the first study of accented TTS synthesis with explicit intensity control.
  arXiv  Detail & Related papers  (2022-09-22T06:13:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.