arXiv Computation and Language September 25, 2026 By Yoomee Cho, Jisun Lee

Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

Read the original on arXiv Computation and Language →

The paper introduces Accent Analogy Guidance (AAG), a training‑free sampling technique that removes accent influence from synthetic voices in cross‑lingual zero‑shot text‑to‑speech. By subtracting an accent direction derived from the model’s own predictions, AAG improves speaker similarity while maintaining the same accent level. Experiments on four open TTS models show that AAG consistently outperforms reweighting methods, achieving higher speaker similarity scores across multiple test sets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Jul 7

GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech

arXiv:2607. 02633v1 Announce Type: new Abstract: We present GRAFT, a per-word pronunciation conditioning mechanism for text-to-speech neural codec language modeling.

By Antonis Asonitis, Francesco Verdini, Aref Farhadipour, Vijeta Avijeet, Pierre-Edouard Honnet, Marzieh Razavi, Juan Pablo Zuluaga Gomez

nlp multimodal benchmarks

Hugging Face Trending Papers

Aug 12

Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.

llms multimodal benchmarks

arXiv Computation and Language

Sep 15

Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech

arXiv:2609.14817v1 Announce Type: new Abstract: In Yor\`ub\'a, pitch alone separates \d{o}k\d{o} (husband, Mid), \d{o}k\d{\`o} (vehicle, Low), and \d{o}k\d{\'o} (hoe, High) -- the diacritics ARE the...

By Moses Daudu, Adeola Enitan Bamidele, Honor-Jesus Bezaleel

fine-tuning multimodal

arXiv Computation and Language

Sep 15

Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy Distillation

arXiv:2609.15313v1 Announce Type: cross Abstract: Autoregressive generation of interleaved text and acoustic tokens is a common approach to spoken-response generation in speech large language models....

By Daxin Tan, Dehua Tao, Chengxi Deng, Hanlin Zhang, Xiao Chen

llms fine-tuning efficiency multimodal

arXiv Machine Learning

Aug 28

Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units

The paper introduces ABX-Accent, a benchmark built on the AESRC dataset that evaluates how well representation learning models adapt to 10 different English accents with less than 10 hours of unlabeled data per accent. It adapts the Zero Resources Challenge ABX metrics for each accent and demonstrates a baseline using adaptive domain normalization to fine‑tune a Contrastive Predictive Coding model, achieving a 23.6% relative improvement on across‑speaker ABX scores compared to non‑adapted models. The dataset and evaluation metrics will be released publicly after the paper is accepted.

By Robin San Roman, Manel Khentout, Tu Anh Nguyen, Paul Michel, Yossi Adi, Emmanuel Dupoux

benchmarks

arXiv AI

Sep 2

Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

The paper investigates whether audio‑language models capture paralinguistic cues beyond spoken content. Using the Expresso dataset and four open‑source models, the authors trace how speaking style information is encoded in the late layers of the audio encoder but is degraded before reaching the final output. They find that some models are content‑driven while others are acoustic‑driven, revealing a gap between what is encoded and what is utilized in current audio‑language models.

By Bhuvan Koduru, Dareen Safar B Alharthi, Rita Singh, Bhiksha Raj

llms multimodal safety