Imagen de Portada

Effective internal language model training and fusion for factorized transducer model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Jinxi, Moritz, Niko, Ma, Yingyi, Seide, Frank, Wu, Chunyang, Mahadeokar, Jay, Kalinli, Ozlem, Fuegen, Christian, Seltzer, Mike
Formato:	Preprint
Publicado:	2024
Materias:	Audio and Speech Processing Artificial Intelligence Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
por: Deng, Keqi, et al.
Publicado: (2024)

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

Faster Speech-LLaMA Inference with Multi-token Prediction
por: Raj, Desh, et al.
Publicado: (2024)

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

Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning
por: Ma, Yingyi, et al.
Publicado: (2024)

AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition
por: Lin, Ju, et al.
Publicado: (2024)

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
por: Zhou, Wei, et al.
Publicado: (2024)

Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition
por: Moritz, Niko, et al.
Publicado: (2024)

M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses
por: Yang, Yufeng, et al.
Publicado: (2024)

Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
por: Xie, Jiamin, et al.
Publicado: (2023)

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
por: Kang, Wonjune, et al.
Publicado: (2024)

MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables
por: Yeh, Sung-Lin, et al.
Publicado: (2026)

Towards scalable efficient on-device ASR with transfer learning
por: Pandey, Laxmi, et al.
Publicado: (2024)

Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens
por: Zhao, Jinzheng, et al.
Publicado: (2024)

Token-Weighted RNN-T for Learning from Flawed Data
por: Keren, Gil, et al.
Publicado: (2024)

Towards measuring fairness in speech recognition: Fair-Speech dataset
por: Veliche, Irina-Elena, et al.
Publicado: (2024)

Conversational Speech Naturalness Predictor
por: Xu, Anfeng, et al.
Publicado: (2026)

Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time
por: Seide, Frank, et al.
Publicado: (2024)

Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation
por: Rabatin, Rastislav, et al.
Publicado: (2024)

Directional Source Separation for Robust Speech Recognition on Smart Glasses
por: Feng, Tiantian, et al.
Publicado: (2023)

Towards audio language modeling -- an overview
por: Wu, Haibin, et al.
Publicado: (2024)

Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
por: Shen, Maohao, et al.
Publicado: (2024)

Single-channel speech enhancement by using psychoacoustical model inspired fusion framework
por: Samui, Suman
Publicado: (2022)

SLM-S2ST: A multimodal language model for direct speech-to-speech translation
por: Hu, Yuxuan, et al.
Publicado: (2025)

Speaker anonymization using neural audio codec language models
por: Panariello, Michele, et al.
Publicado: (2023)

Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training
por: Ahmad, Rehan, et al.
Publicado: (2024)

PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers
por: Pandey, Rahul, et al.
Publicado: (2023)

Selecting N-lowest scores for training MOS prediction models
por: Kondo, Yuto, et al.
Publicado: (2025)

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

Bridging the gap between training and inference in LM-based TTS models
por: Zhang, Ruonan, et al.
Publicado: (2025)

Building English ASR model with regional language support
por: Agrawal, Purvi, et al.
Publicado: (2025)

ParaCLAP -- Towards a general language-audio model for computational paralinguistic tasks
por: Jing, Xin, et al.
Publicado: (2024)

How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses
por: Leer, Peter, et al.
Publicado: (2024)

Self-consistent context aware conformer transducer for speech recognition
por: Kolokolov, Konstantin, et al.
Publicado: (2024)

Encoding of lexical tone in self-supervised models of spoken language
por: Shen, Gaofei, et al.
Publicado: (2024)

Mellow: a small audio language model for reasoning
por: Deshmukh, Soham, et al.
Publicado: (2025)

Understanding the strengths and weaknesses of SSL models for audio deepfake model attribution
por: Pîrlogeanu, Gabriel, et al.
Publicado: (2026)

Towards interfacing large language models with ASR systems using confidence measures and prompting
por: Naderi, Maryam, et al.
Publicado: (2024)

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

AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs
por: Fathullah, Yassir, et al.
Publicado: (2023)