Imagen de Portada

Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Dingdong, Li, Junan, Cui, Mingyu, Yang, Dongchao, Chen, Xueyuan, Meng, Helen
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Sound
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models
por: Wang, Dingdong, et al.
Publicado: (2024)

MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
por: Wang, Dingdong, et al.
Publicado: (2025)

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

SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
por: Yang, Dongchao, et al.
Publicado: (2024)

CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction
por: Chen, Xueyuan, et al.
Publicado: (2024)

Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization
por: Zhao, Mengjie, et al.
Publicado: (2026)

Exploring SSL Discrete Tokens for Multilingual ASR
por: Cui, Mingyu, et al.
Publicado: (2024)

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

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models
por: Wang, Yuanyuan, et al.
Publicado: (2025)

DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding
por: Shon, Suwon, et al.
Publicado: (2024)

On the Evaluation of Speech Foundation Models for Spoken Language Understanding
por: Arora, Siddhant, et al.
Publicado: (2024)

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
por: Tseng, Liang-Hsuan, et al.
Publicado: (2025)

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR
por: Cui, Mingyu, et al.
Publicado: (2024)

ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs
por: Mousavi, Pooneh, et al.
Publicado: (2025)

TASTE-Streaming: Towards Streamable Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
por: Tseng, Liang-Hsuan, et al.
Publicado: (2026)

Continuous Speech Tokenizer in Text To Speech
por: Li, Yixing, et al.
Publicado: (2024)

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

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

NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
por: Wang, Qichao, et al.
Publicado: (2025)

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
por: Zhang, Xin, et al.
Publicado: (2023)

SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models
por: Yang, Dongchao, et al.
Publicado: (2024)

Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
por: Jung, Yeonjoon, et al.
Publicado: (2024)

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

Continual Speech Learning with Fused Speech Features
por: Wang, Guitao, et al.
Publicado: (2025)

DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
por: Chang, Heng-Jui, et al.
Publicado: (2024)

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training
por: Wang, Dingdong, et al.
Publicado: (2025)

DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model
por: Chen, Xueyuan, et al.
Publicado: (2025)

Benchmarking Prosody Encoding in Discrete Speech Tokens
por: Onda, Kentaro, et al.
Publicado: (2025)

End-to-end Contrastive Language-Speech Pretraining Model For Long-form Spoken Question Answering
por: Hu, Jiliang, et al.
Publicado: (2025)

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

Long-Form Speech Generation with Spoken Language Models
por: Park, Se Jin, et al.
Publicado: (2024)

Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
por: Huang, Kuan-Po, et al.
Publicado: (2023)

EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
por: Wang, Dingdong, et al.
Publicado: (2026)

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

Rethinking Discrete Speech Representation Tokens for Accent Generation
por: Zhong, Jinzuomu, et al.
Publicado: (2026)

Children's Speech Recognition through Discrete Token Enhancement
por: Sukhadia, Vrunda N., et al.
Publicado: (2024)

Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
por: Kang, Jiawen, et al.
Publicado: (2024)

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

Evaluating and Improving Continual Learning in Spoken Language Understanding
por: Yang, Muqiao, et al.
Publicado: (2024)

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
por: Wang, Yuancheng, et al.
Publicado: (2025)