Optimizing Multilingual Text-To-Speech with Accents & Emotions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pawar, Pranav, Dwivedi, Akshansh, Boricha, Jenish, Gohil, Himanshu, Dubey, Aditya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918065552228352
author Pawar, Pranav
Dwivedi, Akshansh
Boricha, Jenish
Gohil, Himanshu
Dubey, Aditya
author_facet Pawar, Pranav
Dwivedi, Akshansh
Boricha, Jenish
Gohil, Himanshu
Dubey, Aditya
contents State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty owing to cultural nuance discrepancies in current frameworks. This paper introduces a new TTS architecture integrating accent along with preserving transliteration with multi-scale emotion modelling, in particularly tuned for Hindi and Indian English accent. Our approach extends the Parler-TTS model by integrating A language-specific phoneme alignment hybrid encoder-decoder architecture, and culture-sensitive emotion embedding layers trained on native speaker corpora, as well as incorporating a dynamic accent code switching with residual vector quantization. Quantitative tests demonstrate 23.7% improvement in accent accuracy (Word Error Rate reduction from 15.4% to 11.8%) and 85.3% emotion recognition accuracy from native listeners, surpassing METTS and VECL-TTS baselines. The novelty of the system is that it can mix code in real time - generating statements such as "Namaste, let's talk about <Hindi phrase>" with uninterrupted accent shifts while preserving emotional consistency. Subjective evaluation with 200 users reported a mean opinion score (MOS) of 4.2/5 for cultural correctness, much better than existing multilingual systems (p<0.01). This research makes cross-lingual synthesis more feasible by showcasing scalable accent-emotion disentanglement, with direct application in South Asian EdTech and accessibility software.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16310
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimizing Multilingual Text-To-Speech with Accents & Emotions
Pawar, Pranav
Dwivedi, Akshansh
Boricha, Jenish
Gohil, Himanshu
Dubey, Aditya
Machine Learning
Human-Computer Interaction
Sound
Audio and Speech Processing
State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty owing to cultural nuance discrepancies in current frameworks. This paper introduces a new TTS architecture integrating accent along with preserving transliteration with multi-scale emotion modelling, in particularly tuned for Hindi and Indian English accent. Our approach extends the Parler-TTS model by integrating A language-specific phoneme alignment hybrid encoder-decoder architecture, and culture-sensitive emotion embedding layers trained on native speaker corpora, as well as incorporating a dynamic accent code switching with residual vector quantization. Quantitative tests demonstrate 23.7% improvement in accent accuracy (Word Error Rate reduction from 15.4% to 11.8%) and 85.3% emotion recognition accuracy from native listeners, surpassing METTS and VECL-TTS baselines. The novelty of the system is that it can mix code in real time - generating statements such as "Namaste, let's talk about <Hindi phrase>" with uninterrupted accent shifts while preserving emotional consistency. Subjective evaluation with 200 users reported a mean opinion score (MOS) of 4.2/5 for cultural correctness, much better than existing multilingual systems (p<0.01). This research makes cross-lingual synthesis more feasible by showcasing scalable accent-emotion disentanglement, with direct application in South Asian EdTech and accessibility software.
title Optimizing Multilingual Text-To-Speech with Accents & Emotions
topic Machine Learning
Human-Computer Interaction
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.16310