LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization

• URL: http://arxiv.org/abs/2509.05863v1
• Date: Sat, 06 Sep 2025 23:36:30 GMT
• Title: LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization
• Abstract summary: We present LatinX, a multilingual text-to-speech (TTS) model for cascaded speech-to-speech translation.<n>LatinX is trained in three stages: (i) pre-training for text-to-audio mapping, (ii) supervised fine-tuning for zero-shot voice cloning, and (iii) alignment with Direct Preference Optimization.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present LatinX, a multilingual text-to-speech (TTS) model for cascaded speech-to-speech translation that preserves the source speaker's identity across languages. LatinX is a 12-layer decoder-only Transformer trained in three stages: (i) pre-training for text-to-audio mapping, (ii) supervised fine-tuning for zero-shot voice cloning, and (iii) alignment with Direct Preference Optimization (DPO) using automatically labeled pairs based on Word Error Rate (WER) and speaker-similarity metrics. Trained on English and Romance languages with emphasis on Portuguese, LatinX with DPO consistently reduces WER and improves objective similarity over the fine-tuned baseline. Human evaluations further indicate stronger perceived speaker similarity than a strong baseline (XTTSv2), revealing gaps between objective and subjective measures. We provide cross-lingual analyses and discuss balanced preference signals and lower-latency architectures as future work.

Related papers

• PRiSM: Benchmarking Phone Realization in Speech Models [70.82595415252682]
  Phone recognition (PR) serves as the atomic interface for language-agnostic modeling for cross-lingual speech processing and phonetic analysis.<n>We introduce PRiSM, the first open-source benchmark designed to expose blind spots in phonetic perception.
  arXiv  Detail & Related papers  (2026-01-20T15:00:36Z)
• ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction [88.41471266579333]
  We propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models.<n> Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones show significant improvements.
  arXiv  Detail & Related papers  (2025-11-09T08:50:11Z)
• Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization [13.222167833914924]
  We propose a framework to adapt an autoregressive, multilingual TTS model to new languages.<n>We fine-tune this model on limited paired data of the new languages to capture the target language's prosodic features.<n>Experiments demonstrate that this pipeline produces intelligible and speaker-consistent speech in low-resource languages.
  arXiv  Detail & Related papers  (2025-09-26T00:28:50Z)
• Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings [0.0]
  We propose WSI (Whisper Speaker Identification), a framework that repurposes the Whisper automatic speech recognition model pre trained on extensive multilingual data.<n>By capitalizing on Whisper language-agnostic acoustic representations, our approach effectively distinguishes speakers across diverse languages.
  arXiv  Detail & Related papers  (2025-03-13T15:11:28Z)
• An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios [76.11409260727459]
  This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance.
  arXiv  Detail & Related papers  (2024-06-13T08:16:52Z)
• Towards a Deep Understanding of Multilingual End-to-End Speech Translation [52.26739715012842]
  We analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. We derive three major findings from our analysis.
  arXiv  Detail & Related papers  (2023-10-31T13:50:55Z)
• The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation [13.352795145385645]
  Speech translation (ST) is a good means of pretraining speech models for end-to-end spoken language understanding. We show that our models reach higher performance over baselines on monolingual and multilingual intent classification. We also create new benchmark datasets for speech summarization and low-resource/zero-shot transfer from English to French or Spanish.
  arXiv  Detail & Related papers  (2023-05-16T17:53:03Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation [11.336431583289382]
  This paper presents a method for end-to-end cross-lingual text-to-speech. It aims to preserve the target language's pronunciation regardless of the original speaker's language.
  arXiv  Detail & Related papers  (2022-10-31T12:44:53Z)
• Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition [31.575930914290762]
  A novel data-driven approach is proposed to investigate the cross-lingual acoustic-phonetic similarities. Deep neural networks are trained as mapping networks to transform the distributions from different acoustic models into a directly comparable form. A relative improvement of 8% over monolingual counterpart is achieved.
  arXiv  Detail & Related papers  (2022-07-07T15:55:41Z)
• Cross-lingual Low Resource Speaker Adaptation Using Phonological Features [2.8080708404213373]
  We train a language-agnostic multispeaker model conditioned on a set of phonologically derived features common across different languages. With as few as 32 and 8 utterances of target speaker data, we obtain high speaker similarity scores and naturalness comparable to the corresponding literature.
  arXiv  Detail & Related papers  (2021-11-17T12:33:42Z)
• Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech [62.95422526044178]
  We use Model Agnostic Meta-Learning (MAML) as the training algorithm of a multi-speaker TTS model. We show that Meta-TTS can synthesize high speaker-similarity speech from few enrollment samples with fewer adaptation steps than the speaker adaptation baseline.
  arXiv  Detail & Related papers  (2021-11-07T09:53:31Z)
• Cross-lingual Spoken Language Understanding with Regularized Representation Alignment [71.53159402053392]
  We propose a regularization approach to align word-level and sentence-level representations across languages without any external resource. Experiments on the cross-lingual spoken language understanding task show that our model outperforms current state-of-the-art methods in both few-shot and zero-shot scenarios.
  arXiv  Detail & Related papers  (2020-09-30T08:56:53Z)

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.