paper-with-me

Papers

SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data

2024-02-10 · Hsuan-Fu Wang, Yi-Jen Shih, Heng-Jui Chang, Layne Berry, Puyuan Peng, Hung-Yi Lee, Hsin-Min Wang, David Harwath

The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to SpeechCLIP. First, we apply the Continuous Integrate-and-Fire (CIF) module to replace a fixed number of CLS tokens in the cascaded architecture. Second, we propose a new hybrid architecture that merges the cascaded and parallel architectures of SpeechCLIP into a multi-task learning framework. Our experimental evaluation is performed on the Flickr8k and SpokenCOCO datasets. The results show that in the speech keyword extraction task, the CIF-based cascaded SpeechCLIP model outperforms the previous cascaded SpeechCLIP model using a fixed number of CLS tokens. Furthermore, through our hybrid architecture, cascaded task learning boosts the performance of the parallel branch in image-speech retrieval tasks.

📄 PDF Abstract BibTeX arXiv:2402.06959

Code (1)

ShampooWang/SpeechCLIP_plus 공식 구현 pytorch

Tasks

Keyword ExtractionMulti-Task LearningRepresentation LearningRetrieval

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model

2022-10-03 · Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry 외

Data-driven speech processing models usually perform well with a large amount of text supervision, but collecting transcribed speech data is costly. Therefore, we propose SpeechCLIP, a novel framework bridging speech and…

Language ModelingLanguage ModellingRetrievalText Retrieval

Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning

2023-09-08 · Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velazquez, Thomas Thebaud 외

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, s…

audio-visual learningQuantizationWord Embeddings

M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval

2022-11-02 · Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang 외

This work investigates the use of large-scale, English-only pre-trained models (CLIP and HuBERT) for multilingual image-speech retrieval. For non-English image-speech retrieval, we outperform the current state-of-the-art…

Image RetrievalRetrievalText Retrieval

Self-supervised Learning from a Multi-view Perspective

2020-06-10 · ICLR 2021 1 · Yao-Hung Hubert Tsai, Yue Wu, Ruslan Salakhutdinov, Louis-Philippe Morency

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection a…

Image CaptioningLanguage Modellingobject-detectionObject Detection+2

On the robustness of self-supervised representations for multi-view object classification

2022-07-27 · David Torpey, Richard Klein

It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training. This has been shown in a host …

Image RetrievalObjectRetrievalSemantic Segmentation