Imagen de Portada

Pheme: Efficient and Conversational Speech Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Budzianowski, Paweł, Sereda, Taras, Cichy, Tomasz, Vulić, Ivan
Formato:	Preprint
Publicado:	2024
Materias:	Audio and Speech Processing Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Transcribe, Align and Segment: Creating speech datasets for low-resource languages
por: Sereda, Taras
Publicado: (2024)

Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones
por: Teleki, Maria, et al.
Publicado: (2025)

KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI
por: Kuroki, So, et al.
Publicado: (2025)

StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction
por: Xu, Qianheng
Publicado: (2025)

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations
por: Saengthong, Phurich, et al.
Publicado: (2025)

Speech Retrieval-Augmented Generation without Automatic Speech Recognition
por: Min, Do June, et al.
Publicado: (2024)

Dual Information Speech Language Models for Emotional Conversations
por: Wang, Chun, et al.
Publicado: (2025)

COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning
por: Pan, Jing, et al.
Publicado: (2023)

MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
por: Zhang, He, et al.
Publicado: (2025)

What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
por: Fan, Xiaoran, et al.
Publicado: (2025)

Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation
por: Fejgin, Roy, et al.
Publicado: (2025)

FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model
por: Lu, Yichen, et al.
Publicado: (2024)

Efficient Streaming LLM for Speech Recognition
por: Jia, Junteng, et al.
Publicado: (2024)

Phonology-Guided Speech-to-Speech Translation for African Languages
por: Ochieng, Peter, et al.
Publicado: (2024)

Streaming Speech-to-Text Translation with a SpeechLLM
por: Parcollet, Titouan, et al.
Publicado: (2026)

Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models
por: Ognjen, et al.
Publicado: (2024)

Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
por: Gedeon, Máté, et al.
Publicado: (2025)

LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition
por: Ghosh, Sreyan, et al.
Publicado: (2024)

Efficient Compression of Multitask Multilingual Speech Models
por: Ferraz, Thomas Palmeira
Publicado: (2024)

WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
por: Yang, Guanrou, et al.
Publicado: (2026)

TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers
por: Song, Yakun, et al.
Publicado: (2024)

Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks
por: Hsu, Ming-Hao, et al.
Publicado: (2023)

MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond
por: Huzaifah, Muhammad, et al.
Publicado: (2024)

SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation
por: Djanibekov, Amirbek, et al.
Publicado: (2026)

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
por: Wang, Qiongqiong, et al.
Publicado: (2025)

Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations Generation
por: Gkritzali, Evangelia, et al.
Publicado: (2024)

A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation
por: Ma, Zhengrui, et al.
Publicado: (2024)

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects
por: Yang, Sicheng, et al.
Publicado: (2026)

Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation
por: Li, Yinghao Aaron, et al.
Publicado: (2024)

Handling Numeric Expressions in Automatic Speech Recognition
por: Huber, Christian, et al.
Publicado: (2024)

Can Speech LLMs Think while Listening?
por: Shih, Yi-Jen, et al.
Publicado: (2025)

MultiGen: Child-Friendly Multilingual Speech Generator with LLMs
por: Gao, Xiaoxue, et al.
Publicado: (2025)

Linear-Complexity Self-Supervised Learning for Speech Processing
por: Zhang, Shucong, et al.
Publicado: (2024)

Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
por: Zhang, Shucong, et al.
Publicado: (2025)

HARNESS: Lightweight Distilled Arabic Speech Foundation Models
por: Sukhadia, Vrunda N., et al.
Publicado: (2026)

Closing the Gap Between Text and Speech Understanding in LLMs
por: Cuervo, Santiago, et al.
Publicado: (2025)

Unifying Model and Layer Fusion for Speech Foundation Models
por: Shih, Yi-Jen, et al.
Publicado: (2025)

ARTI-6: Towards Six-dimensional Articulatory Speech Encoding
por: Lee, Jihwan, et al.
Publicado: (2025)

Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
por: Wang, Qiongqiong, et al.
Publicado: (2025)

Towards Robust Speech Recognition for Jamaican Patois Music Transcription
por: Madden, Jordan, et al.
Publicado: (2025)