Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing

• URL: http://arxiv.org/abs/2406.06582v2
• Date: Tue, 25 Jun 2024 17:44:00 GMT
• Title: Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing
• Authors: Viet Anh Trinh, Rosy Southwell, Yiwen Guan, Xinlu He, Zhiyong Wang, Jacob Whitehill,
• Abstract summary: We present a decoder-only Discrete Multimodal Language Model (DMLM) DMLM can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision) Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training.
• Score: 17.92378239787507
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions [68.98811048970963]
  We present a pioneering effort to investigate the capability of large language models (LLMs) in transcribing speech in multi-talker environments. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios.
  arXiv  Detail & Related papers  (2024-09-13T07:28:28Z)
• WavLLM: Towards Robust and Adaptive Speech Large Language Model [93.0773293897888]
  We introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter. We validate the proposed model on universal speech benchmarks including tasks such as ASR, ST, SV, ER, and also apply it to specialized datasets like Gaokao English listening comprehension set for SQA, and speech Chain-of-Thought (CoT) evaluation set.
  arXiv  Detail & Related papers  (2024-03-31T12:01:32Z)
• AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling [115.89786751297348]
  We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities. We build a multimodal text-centric dataset for multimodal alignment pre-training. We show that AnyGPT is capable of facilitating any-to-any multimodal conversation while achieving performance comparable to specialized models across all modalities.
  arXiv  Detail & Related papers  (2024-02-19T15:33:10Z)
• ModaVerse: Efficiently Transforming Modalities with LLMs [25.49713745405194]
  We introduce ModaVerse, a Multi-modal Large Language Model capable of comprehending and transforming content across various modalities. We propose a novel Input/Output (I/O) alignment mechanism that operates directly at the level of natural language.
  arXiv  Detail & Related papers  (2024-01-12T06:28:54Z)
• Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration [50.94902442781148]
  We propose a novel multi-modal large language model (LLM) that seamlessly integrates visual, audio, and textual information. Macaw-LLM consists of three main components: a modality module for encoding multi-modal data, a cognitive module for harnessing pretrained LLMs, and an alignment module for harmonizing diverse representations. We construct a large-scale multi-modal instruction dataset in terms of multi-turn dialogue, including 69K image instances and 50K video instances.
  arXiv  Detail & Related papers  (2023-06-15T12:45:25Z)
• TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models [5.668457303716451]
  We propose TextMI as a general, competitive baseline for multimodal behavioral analysis tasks. Our approach significantly reduces model complexity, adds interpretability to the model's decision, and can be applied for a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-03-27T17:54:32Z)
• Unsupervised Multimodal Language Representations using Convolutional Autoencoders [5.464072883537924]
  We propose extracting unsupervised Multimodal Language representations that are universal and can be applied to different tasks. We map the word-level aligned multimodal sequences to 2-D matrices and then use Convolutional Autoencoders to learn embeddings by combining multiple datasets. It is also shown that our method is extremely lightweight and can be easily generalized to other tasks and unseen data with small performance drop and almost the same number of parameters.
  arXiv  Detail & Related papers  (2021-10-06T18:28:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.