Buchumschlag

Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhao, Mengjie, Liu, Lianbo, Fujita, Yusuke, Shi, Hao, Gao, Yuan, Koshkin, Roman, Sudo, Yui
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Sound Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Distilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing
von: Shi, Hao, et al.
Veröffentlicht: (2026)

Streaming Translation and Transcription Through Speech-to-Text Causal Alignment
von: Koshkin, Roman, et al.
Veröffentlicht: (2026)

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
von: Sudo, Yui, et al.
Veröffentlicht: (2025)

Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition
von: Shi, Hao, et al.
Veröffentlicht: (2025)

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation
von: Fujita, Yusuke, et al.
Veröffentlicht: (2025)

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs
von: Song, Yuhan, et al.
Veröffentlicht: (2025)

Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs
von: Wang, Dingdong, et al.
Veröffentlicht: (2025)

The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs
von: Satish, Shree Harsha Bokkahalli, et al.
Veröffentlicht: (2026)

OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification
von: Peng, Yifan, et al.
Veröffentlicht: (2024)

Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation
von: Shakeel, Muhammad, et al.
Veröffentlicht: (2024)

DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization
von: Yang, Jianing, et al.
Veröffentlicht: (2026)

Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss
von: Shakeel, Muhammad, et al.
Veröffentlicht: (2024)

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs
von: Quang, Trung Nguyen, et al.
Veröffentlicht: (2026)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary
von: Sudo, Yui, et al.
Veröffentlicht: (2024)

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
von: Papi, Sara, et al.
Veröffentlicht: (2026)

Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search
von: Sudo, Yui, et al.
Veröffentlicht: (2024)

Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment
von: Parikh, Aditya Kamlesh, et al.
Veröffentlicht: (2026)

Emotion-Aligned Generation in Diffusion Text to Speech Models via Preference-Guided Optimization
von: Shi, Jiacheng, et al.
Veröffentlicht: (2025)

DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
von: Sudo, Yui, et al.
Veröffentlicht: (2025)

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning
von: Peng, Yifan, et al.
Veröffentlicht: (2025)

Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs
von: Satish, Shree Harsha Bokkahalli, et al.
Veröffentlicht: (2025)

Speech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme Duration for Multi-Speaker Speech Synthesis
von: Fujita, Kenichi, et al.
Veröffentlicht: (2024)

Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?
von: Pareras, Oriol, et al.
Veröffentlicht: (2025)

Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
von: Nguyen, Tuan, et al.
Veröffentlicht: (2025)

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
von: Wang, Hui, et al.
Veröffentlicht: (2025)

PART: Progressive Alignment Representation Training for Multilingual Speech-To-Text with LLMs
von: Zhang, Pei, et al.
Veröffentlicht: (2025)

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
von: Ma, Rao, et al.
Veröffentlicht: (2025)

Soundwave: Less is More for Speech-Text Alignment in LLMs
von: Zhang, Yuhao, et al.
Veröffentlicht: (2025)

S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation
von: Pan, Yu, et al.
Veröffentlicht: (2025)

POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation
von: Li, Xuanchen, et al.
Veröffentlicht: (2025)

Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
von: Fujita, Kenichi, et al.
Veröffentlicht: (2024)

When Voice Matters: Evidence of Gender Disparity in Positional Bias of SpeechLLMs
von: Satish, Shree Harsha Bokkahalli, et al.
Veröffentlicht: (2025)

Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers
von: Hentschel, Michael, et al.
Veröffentlicht: (2024)

Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation
von: Liu, Henglyu, et al.
Veröffentlicht: (2025)

SpeechAlign: Aligning Speech Generation to Human Preferences
von: Zhang, Dong, et al.
Veröffentlicht: (2024)

TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment
von: Kim, Taesoo, et al.
Veröffentlicht: (2025)

Direct Speech to Speech Translation: A Review
von: Sarim, Mohammad, et al.
Veröffentlicht: (2025)

AlignCap: Aligning Speech Emotion Captioning to Human Preferences
von: Liang, Ziqi, et al.
Veröffentlicht: (2024)

Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
von: Futami, Hayato, et al.
Veröffentlicht: (2025)

Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
von: Kando, Shunsuke, et al.
Veröffentlicht: (2025)