Guardado en:
Detalles Bibliográficos
Autores principales: Trinh, Viet Anh, Southwell, Rosy, Guan, Yiwen, He, Xinlu, Wang, Zhiyong, Whitehill, Jacob
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.06582
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916299684184064
author Trinh, Viet Anh
Southwell, Rosy
Guan, Yiwen
He, Xinlu
Wang, Zhiyong
Whitehill, Jacob
author_facet Trinh, Viet Anh
Southwell, Rosy
Guan, Yiwen
He, Xinlu
Wang, Zhiyong
Whitehill, Jacob
contents Recent work on discrete speech tokenization has paved the way for models that can seamlessly perform multiple tasks across modalities, e.g., speech recognition, text to speech, speech to speech translation. Moreover, large language models (LLMs) pretrained from vast text corpora contain rich linguistic information that can improve accuracy in a variety of tasks. In this paper, we present a decoder-only Discrete Multimodal Language Model (DMLM), which can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision). We explore several critical aspects of discrete multi-modal models, including the loss function, weight initialization, mixed training supervision, and codebook. Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training. Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06582
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
Trinh, Viet Anh
Southwell, Rosy
Guan, Yiwen
He, Xinlu
Wang, Zhiyong
Whitehill, Jacob
Computation and Language
Machine Learning
Audio and Speech Processing
Recent work on discrete speech tokenization has paved the way for models that can seamlessly perform multiple tasks across modalities, e.g., speech recognition, text to speech, speech to speech translation. Moreover, large language models (LLMs) pretrained from vast text corpora contain rich linguistic information that can improve accuracy in a variety of tasks. In this paper, we present a decoder-only Discrete Multimodal Language Model (DMLM), which can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision). We explore several critical aspects of discrete multi-modal models, including the loss function, weight initialization, mixed training supervision, and codebook. Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training. Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.
title Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
topic Computation and Language
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2406.06582