Alert button

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

Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM

Sep 08, 2022
Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Figure 1 for Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Figure 2 for Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Figure 3 for Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Figure 4 for Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM
Viaarxiv icon

Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis

Jul 27, 2021
Shifeng Pan, Lei He

Figure 1 for Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
Figure 2 for Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
Figure 3 for Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
Figure 4 for Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis
Viaarxiv icon

A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification

Feb 05, 2022
Yves Bestgen

Figure 1 for A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
Figure 2 for A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
Figure 3 for A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
Figure 4 for A simple language-agnostic yet very strong baseline system for hate speech and offensive content identification
Viaarxiv icon

Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis

Sep 29, 2022
Shivam Sharma, Mohd Khizir Siddiqui, Md. Shad Akhtar, Tanmoy Chakraborty

Figure 1 for Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
Figure 2 for Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
Figure 3 for Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
Figure 4 for Domain-aware Self-supervised Pre-training for Label-Efficient Meme Analysis
Viaarxiv icon

Speech recognition for air traffic control via feature learning and end-to-end training

Nov 04, 2021
Peng Fan, Dongyue Guo, Yi Lin, Bo Yang, Jianwei Zhang

Figure 1 for Speech recognition for air traffic control via feature learning and end-to-end training
Figure 2 for Speech recognition for air traffic control via feature learning and end-to-end training
Figure 3 for Speech recognition for air traffic control via feature learning and end-to-end training
Figure 4 for Speech recognition for air traffic control via feature learning and end-to-end training
Viaarxiv icon

Automatic Speaker Independent Dysarthric Speech Intelligibility Assessment System

Mar 10, 2021
Ayush Tripathi, Swapnil Bhosale, Sunil Kumar Kopparapu

Figure 1 for Automatic Speaker Independent Dysarthric Speech Intelligibility Assessment System
Figure 2 for Automatic Speaker Independent Dysarthric Speech Intelligibility Assessment System
Figure 3 for Automatic Speaker Independent Dysarthric Speech Intelligibility Assessment System
Figure 4 for Automatic Speaker Independent Dysarthric Speech Intelligibility Assessment System
Viaarxiv icon

Universal Fourier Attack for Time Series

Sep 02, 2022
Elizabeth Coda, Brad Clymer, Chance DeSmet, Yijing Watkins, Michael Girard

Figure 1 for Universal Fourier Attack for Time Series
Figure 2 for Universal Fourier Attack for Time Series
Figure 3 for Universal Fourier Attack for Time Series
Figure 4 for Universal Fourier Attack for Time Series
Viaarxiv icon

Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators

Nov 03, 2021
Marko Stamenovic, Nils L. Westhausen, Li-Chia Yang, Carl Jensen, Alex Pawlicki

Figure 1 for Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
Figure 2 for Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
Figure 3 for Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
Figure 4 for Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators
Viaarxiv icon

How Adults Understand What Young Children Say

Jun 15, 2022
Stephan C. Meylan, Ruthe Foushee, Nicole H. Wong, Elika Bergelson, Roger P. Levy

Figure 1 for How Adults Understand What Young Children Say
Figure 2 for How Adults Understand What Young Children Say
Figure 3 for How Adults Understand What Young Children Say
Figure 4 for How Adults Understand What Young Children Say
Viaarxiv icon

End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study

Feb 19, 2021
Prashanth Gurunath Shivakumar, Shrikanth Narayanan

Figure 1 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 2 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 3 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Figure 4 for End-to-End Neural Systems for Automatic Children Speech Recognition: An Empirical Study
Viaarxiv icon