Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Mengjie, Liu, Lianbo, Fujita, Yusuke, Shi, Hao, Gao, Yuan, Koshkin, Roman, Sudo, Yui
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.12565
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915858638438400
author Zhao, Mengjie
Liu, Lianbo
Fujita, Yusuke
Shi, Hao
Gao, Yuan
Koshkin, Roman
Sudo, Yui
author_facet Zhao, Mengjie
Liu, Lianbo
Fujita, Yusuke
Shi, Hao
Gao, Yuan
Koshkin, Roman
Sudo, Yui
contents SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is particularly pronounced in Japanese, where spoken and written registers differ substantially in politeness markers, sentence-final particles, and syntactic complexity. We propose a preference-based alignment approach to adapt Japanese SpeechLLMs for speech-worthy outputs: text that is concise, conversational, and readily synthesized as natural speech. To rigorously evaluate this task, we introduce SpokenElyza, a benchmark for Japanese speech-worthiness derived from ELYZA-tasks-100 with auditory verification by native experts. Experiments show that our approach achieves substantial improvement on SpokenElyza while largely preserving performance on the original written-style evaluation. We will release SpokenElyza to support future research on Japanese spoken dialog systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12565
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
Zhao, Mengjie
Liu, Lianbo
Fujita, Yusuke
Shi, Hao
Gao, Yuan
Koshkin, Roman
Sudo, Yui
Sound
Computation and Language
SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This mismatch is particularly pronounced in Japanese, where spoken and written registers differ substantially in politeness markers, sentence-final particles, and syntactic complexity. We propose a preference-based alignment approach to adapt Japanese SpeechLLMs for speech-worthy outputs: text that is concise, conversational, and readily synthesized as natural speech. To rigorously evaluate this task, we introduce SpokenElyza, a benchmark for Japanese speech-worthiness derived from ELYZA-tasks-100 with auditory verification by native experts. Experiments show that our approach achieves substantial improvement on SpokenElyza while largely preserving performance on the original written-style evaluation. We will release SpokenElyza to support future research on Japanese spoken dialog systems.
title Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
topic Sound
Computation and Language
url https://arxiv.org/abs/2603.12565