Alert button

"Text": models, code, and papers
Alert button

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

Oct 03, 2022
Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry, Hung-yi Lee, David Harwath

Figure 1 for SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
Figure 2 for SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
Figure 3 for SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
Figure 4 for SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model
Viaarxiv icon

CTC Alignments Improve Autoregressive Translation

Oct 11, 2022
Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W Black, Shinji Watanabe

Figure 1 for CTC Alignments Improve Autoregressive Translation
Figure 2 for CTC Alignments Improve Autoregressive Translation
Figure 3 for CTC Alignments Improve Autoregressive Translation
Figure 4 for CTC Alignments Improve Autoregressive Translation
Viaarxiv icon

Hyperbolic Audio Source Separation

Dec 09, 2022
Darius Petermann, Gordon Wichern, Aswin Subramanian, Jonathan Le Roux

Figure 1 for Hyperbolic Audio Source Separation
Figure 2 for Hyperbolic Audio Source Separation
Figure 3 for Hyperbolic Audio Source Separation
Figure 4 for Hyperbolic Audio Source Separation
Viaarxiv icon

New Results for the Text Recognition of Arabic Maghrib{ī} Manuscripts -- Managing an Under-resourced Script

Nov 29, 2022
Lucas Noëmie, Clément Salah, Chahan Vidal-Gorène

Figure 1 for New Results for the Text Recognition of Arabic Maghrib{ī} Manuscripts -- Managing an Under-resourced Script
Figure 2 for New Results for the Text Recognition of Arabic Maghrib{ī} Manuscripts -- Managing an Under-resourced Script
Figure 3 for New Results for the Text Recognition of Arabic Maghrib{ī} Manuscripts -- Managing an Under-resourced Script
Figure 4 for New Results for the Text Recognition of Arabic Maghrib{ī} Manuscripts -- Managing an Under-resourced Script
Viaarxiv icon

Training language models for deeper understanding improves brain alignment

Dec 21, 2022
Khai Loong Aw, Mariya Toneva

Figure 1 for Training language models for deeper understanding improves brain alignment
Figure 2 for Training language models for deeper understanding improves brain alignment
Figure 3 for Training language models for deeper understanding improves brain alignment
Figure 4 for Training language models for deeper understanding improves brain alignment
Viaarxiv icon

PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition

Dec 21, 2022
Sihao Chen, Senaka Buthpitiya, Alex Fabrikant, Dan Roth, Tal Schuster

Figure 1 for PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
Figure 2 for PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
Figure 3 for PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
Figure 4 for PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognition
Viaarxiv icon

ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement

Dec 21, 2022
Wei-Ning Hsu, Tal Remez, Bowen Shi, Jacob Donley, Yossi Adi

Figure 1 for ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement
Figure 2 for ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement
Figure 3 for ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement
Figure 4 for ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement
Viaarxiv icon

Improving Probabilistic Models in Text Classification via Active Learning

Feb 05, 2022
Mitchell Bosley, Saki Kuzushima, Ted Enamorado, Yuki Shiraito

Figure 1 for Improving Probabilistic Models in Text Classification via Active Learning
Figure 2 for Improving Probabilistic Models in Text Classification via Active Learning
Figure 3 for Improving Probabilistic Models in Text Classification via Active Learning
Figure 4 for Improving Probabilistic Models in Text Classification via Active Learning
Viaarxiv icon

Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction

Oct 30, 2022
Mohamed Suliman, Douglas Leith

Figure 1 for Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction
Figure 2 for Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction
Figure 3 for Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction
Figure 4 for Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction
Viaarxiv icon

An Ensemble Learning Based Approach to Multi-label Power Text Classification for Fault-type Recognition

Apr 13, 2022
Chen Xiaona, Ahmad Tanvir, Ma Yinglong

Figure 1 for An Ensemble Learning Based Approach to Multi-label Power Text Classification for Fault-type Recognition
Figure 2 for An Ensemble Learning Based Approach to Multi-label Power Text Classification for Fault-type Recognition
Figure 3 for An Ensemble Learning Based Approach to Multi-label Power Text Classification for Fault-type Recognition
Figure 4 for An Ensemble Learning Based Approach to Multi-label Power Text Classification for Fault-type Recognition
Viaarxiv icon