Buchumschlag

SLM-S2ST: A multimodal language model for direct speech-to-speech translation

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hu, Yuxuan, Wu, Haibin, Fan, Ruchao, Wang, Xiaofei, Lu, Heng, Qian, Yao, Li, Jinyu
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation
von: Zhao, Rui, et al.
Veröffentlicht: (2024)

Towards Efficient Speech-Text Jointly Decoding within One Speech Language Model
von: Wu, Haibin, et al.
Veröffentlicht: (2025)

AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM
von: Fan, Ruchao, et al.
Veröffentlicht: (2024)

Omni-directional attention mechanism based on Mamba for speech separation
von: Xue, Ke, et al.
Veröffentlicht: (2026)

Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
von: Huang, Ziling, et al.
Veröffentlicht: (2025)

RLBR: Reinforcement Learning with Biasing Rewards for Contextual Speech Large Language Models
von: Ren, Bo, et al.
Veröffentlicht: (2026)

Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio
von: Shi, Mohan, et al.
Veröffentlicht: (2025)

Phoneme-based speech recognition driven by large language models and sampling marginalization
von: Ma, Te, et al.
Veröffentlicht: (2025)

DBMIF: a deep balanced multimodal iterative fusion framework for air- and bone-conduction speech enhancement
von: Wu, Yilei, et al.
Veröffentlicht: (2026)

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

Transferable speech-to-text large language model alignment module
von: Wu, Boyong, et al.
Veröffentlicht: (2024)

Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data
von: Shirahata, Yuma, et al.
Veröffentlicht: (2024)

Robust fine-tuning of speech recognition models via model merging: application to disordered speech
von: Ducorroy, Alexandre, et al.
Veröffentlicht: (2025)

Can large audio language models understand child stuttering speech? speech summarization, and source separation
von: Okocha, Chibuzor, et al.
Veröffentlicht: (2025)

emg2speech: Synthesizing speech from electromyography using self-supervised speech models
von: Gowda, Harshavardhana T., et al.
Veröffentlicht: (2025)

Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
von: Saon, George, et al.
Veröffentlicht: (2025)

Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions
von: Mack, Wolfgang, et al.
Veröffentlicht: (2025)

Predicting speech intelligibility in older adults for speech enhancement using the Gammachirp Envelope Similarity Index, GESI
von: Yamamoto, Ayako, et al.
Veröffentlicht: (2025)

MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis
von: An, Keyu, et al.
Veröffentlicht: (2025)

Good practices for evaluation of synthesized speech
von: Cooper, Erica, et al.
Veröffentlicht: (2025)

An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech
von: Deng, Qingkun, et al.
Veröffentlicht: (2024)

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
von: Zhang, Leying, et al.
Veröffentlicht: (2025)

End-to-end transfer learning for speaker-independent cross-language and cross-corpus speech emotion recognition
von: Tang, Duowei, et al.
Veröffentlicht: (2023)

Prominence-aware automatic speech recognition for conversational speech
von: Linke, Julian, et al.
Veröffentlicht: (2025)

Text-To-Speech with Chain-of-Details: modeling temporal dynamics in speech generation
von: Ma, Jianbo, et al.
Veröffentlicht: (2026)

Exploring speech style spaces with language models: Emotional TTS without emotion labels
von: Chandra, Shreeram Suresh, et al.
Veröffentlicht: (2024)

Direct Punjabi to English speech translation using discrete units
von: Kaur, Prabhjot, et al.
Veröffentlicht: (2024)

IIITH-BUT system for IWSLT 2025 low-resource Bhojpuri to Hindi speech translation
von: Akkiraju, Bhavana, et al.
Veröffentlicht: (2025)

Towards noise-robust speech inversion through multi-task learning with speech enhancement
von: Tabatabaee, Saba, et al.
Veröffentlicht: (2026)

Probing mental health information in speech foundation models
von: de Gennes, Marc, et al.
Veröffentlicht: (2024)

WhisperFlow: speech foundation models in real time
von: Wang, Rongxiang, et al.
Veröffentlicht: (2024)

End-to-end multi-channel speaker extraction and binaural speech synthesis
von: Chi, Cheng, et al.
Veröffentlicht: (2024)

On the relationship between speech and hearing
von: Umesh, Srinivasan, et al.
Veröffentlicht: (2024)

Index-MSR: A high-efficiency multimodal fusion framework for speech recognition
von: Chen, Jinming, et al.
Veröffentlicht: (2025)

Do self-supervised speech and language models extract similar representations as human brain?
von: Chen, Peili, et al.
Veröffentlicht: (2023)

Spatial-Magnifier: Spatial upsampling for multichannel speech enhancement
von: Lee, Dongheon, et al.
Veröffentlicht: (2026)

Strategies for improving low resource speech to text translation relying on pre-trained ASR models
von: Kesiraju, Santosh, et al.
Veröffentlicht: (2023)

TS3-Codec: Transformer-Based Simple Streaming Single Codec
von: Wu, Haibin, et al.
Veröffentlicht: (2024)

On the social bias of speech self-supervised models
von: Lin, Yi-Cheng, et al.
Veröffentlicht: (2024)

Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models
von: Gubian, Michele, et al.
Veröffentlicht: (2025)