T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
- URL: http://arxiv.org/abs/2406.07119v1
- Date: Tue, 11 Jun 2024 10:06:53 GMT
- Title: T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
- Authors: Aoxiong Yin, Haoyuan Li, Kai Shen, Siliang Tang, Yueting Zhuang,
- Abstract summary: We propose a novel dynamic vector quantization (DVA-VAE) model that can adjust the encoding length based on the information density in sign language.
Experiments conducted on the PHOENIX14T dataset demonstrate the effectiveness of our proposed method.
We propose a new large German sign language dataset, PHOENIX-News, which contains 486 hours of sign language videos, audio, and transcription texts.
- Score: 59.57676466961787
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this work, we propose a two-stage sign language production (SLP) paradigm that first encodes sign language sequences into discrete codes and then autoregressively generates sign language from text based on the learned codebook. However, existing vector quantization (VQ) methods are fixed-length encodings, overlooking the uneven information density in sign language, which leads to under-encoding of important regions and over-encoding of unimportant regions. To address this issue, we propose a novel dynamic vector quantization (DVA-VAE) model that can dynamically adjust the encoding length based on the information density in sign language to achieve accurate and compact encoding. Then, a GPT-like model learns to generate code sequences and their corresponding durations from spoken language text. Extensive experiments conducted on the PHOENIX14T dataset demonstrate the effectiveness of our proposed method. To promote sign language research, we propose a new large German sign language dataset, PHOENIX-News, which contains 486 hours of sign language videos, audio, and transcription texts.Experimental analysis on PHOENIX-News shows that the performance of our model can be further improved by increasing the size of the training data. Our project homepage is https://t2sgpt-demo.yinaoxiong.cn.
Related papers
- SignLLM: Sign Languages Production Large Language Models [33.438444361552854]
We introduce the first comprehensive multilingual sign language dataset named Prompt2Sign.
Our dataset transforms a vast array of videos into a streamlined, model-friendly format.
We propose SignLLM, the first multilingual Sign Language Production model.
arXiv Detail & Related papers (2024-05-17T12:01:43Z) - A Data-Driven Representation for Sign Language Production [26.520016084139964]
Sign Language Production aims to automatically translate spoken language sentences into continuous sequences of sign language.
Current state-of-the-art approaches rely on scarce linguistic resources to work.
This paper introduces an innovative solution by transforming the continuous pose generation problem into a discrete sequence generation problem.
arXiv Detail & Related papers (2024-04-17T15:52:38Z) - Gloss-free Sign Language Translation: Improving from Visual-Language
Pretraining [56.26550923909137]
Gloss-Free Sign Language Translation (SLT) is a challenging task due to its cross-domain nature.
We propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-)
Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual and Text Decoder from
arXiv Detail & Related papers (2023-07-27T10:59:18Z) - Cross-modality Data Augmentation for End-to-End Sign Language Translation [66.46877279084083]
End-to-end sign language translation (SLT) aims to convert sign language videos into spoken language texts directly without intermediate representations.
It has been a challenging task due to the modality gap between sign videos and texts and the data scarcity of labeled data.
We propose a novel Cross-modality Data Augmentation (XmDA) framework to transfer the powerful gloss-to-text translation capabilities to end-to-end sign language translation.
arXiv Detail & Related papers (2023-05-18T16:34:18Z) - CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive
Learning [38.83062453145388]
Sign language retrieval consists of two sub-tasks: text-to-sign-video (T2V) retrieval and sign-video-to-text (V2T) retrieval.
We take into account the linguistic properties of both sign languages and natural languages, and simultaneously identify the fine-grained cross-lingual mappings.
Our framework outperforms the pioneering method by large margins on various datasets.
arXiv Detail & Related papers (2023-03-22T17:59:59Z) - Code-Switching Text Generation and Injection in Mandarin-English ASR [57.57570417273262]
We investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T)
We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces.
Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models.
arXiv Detail & Related papers (2023-03-20T09:13:27Z) - Changing the Representation: Examining Language Representation for
Neural Sign Language Production [43.45785951443149]
We apply Natural Language Processing techniques to the first step of the Neural Sign Language Production pipeline.
We use language models such as BERT and Word2Vec to create better sentence level embeddings.
We introduce Text to HamNoSys (T2H) translation, and show the advantages of using a phonetic representation for sign language translation.
arXiv Detail & Related papers (2022-09-16T12:45:29Z) - Explore More Guidance: A Task-aware Instruction Network for Sign
Language Translation Enhanced with Data Augmentation [20.125265661134964]
Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos.
In this work, we propose a task-aware instruction network, namely TIN-SLT, for sign language translation.
arXiv Detail & Related papers (2022-04-12T17:09:44Z) - SimulSLT: End-to-End Simultaneous Sign Language Translation [55.54237194555432]
Existing sign language translation methods need to read all the videos before starting the translation.
We propose SimulSLT, the first end-to-end simultaneous sign language translation model.
SimulSLT achieves BLEU scores that exceed the latest end-to-end non-simultaneous sign language translation model.
arXiv Detail & Related papers (2021-12-08T11:04:52Z) - FILTER: An Enhanced Fusion Method for Cross-lingual Language
Understanding [85.29270319872597]
We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning.
During inference, the model makes predictions based on the text input in the target language and its translation in the source language.
To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
arXiv Detail & Related papers (2020-09-10T22:42:15Z)
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.