Related papers: Learning-free L2-Accented Speech Generation using Phonological Rules

Learning-free L2-Accented Speech Generation using Phonological Rules

URL: http://arxiv.org/abs/2603.07550v1
Date: Sun, 08 Mar 2026 09:22:55 GMT
Title: Learning-free L2-Accented Speech Generation using Phonological Rules
Abstract summary: 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.
Score: 46.06717601946553
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that combines phonological rules with a multilingual TTS model. The rules are applied to phoneme sequences to transform accent at the phoneme level while preserving intelligibility. The method requires no accented training data and enables explicit phoneme-level accent manipulation. We design rule sets for Spanish- and Indian-accented English, modeling systematic differences in consonants, vowels, and syllable structure arising from phonotactic constraints. We analyze the trade-off between phoneme-level duration alignment and accent as realized in speech timing. Experimental results demonstrate effective accent shift while maintaining speech quality.

Related papers

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)
Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training [14.323313455208183]
Inclusive speech technology aims to erase any biases towards specific groups, such as people of certain accent. We propose a TTS model that utilizes a Multi-Level Variational Autoencoder with adversarial learning to address accented speech synthesis and conversion.
arXiv Detail & Related papers (2024-06-03T05:56:02Z)
Learning Speech Representation From Contrastive Token-Acoustic Pretraining [57.08426714676043]
We propose "Contrastive Token-Acoustic Pretraining (CTAP)", which uses two encoders to bring phoneme and speech into a joint multimodal space. The proposed CTAP model is trained on 210k speech and phoneme pairs, achieving minimally-supervised TTS, VC, and ASR.
arXiv Detail & Related papers (2023-09-01T12:35:43Z)
Multilingual Multiaccented Multispeaker TTS with RADTTS [21.234787964238645]
We present a multilingual, multiaccented, multispeaker speech synthesis model based on RADTTS. We demonstrate an ability to control synthesized accent for any speaker in an open-source dataset comprising of 7 accents.
arXiv Detail & Related papers (2023-01-24T22:39:04Z)
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)
Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding [55.989376102986654]
This paper studies a transferable phoneme embedding framework that aims to deal with the cross-lingual text-to-speech problem under the few-shot setting. We propose a framework that consists of a phoneme-based TTS model and a codebook module to project phonemes from different languages into a learned latent space.
arXiv Detail & Related papers (2022-06-27T11:24:40Z)

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