Alert button

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

Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning

Mar 31, 2021
Rina Buoy, Nguonly Taing, Sokchea Kor

Figure 1 for Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning
Figure 2 for Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning
Figure 3 for Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning
Figure 4 for Joint Khmer Word Segmentation and Part-of-Speech Tagging Using Deep Learning
Viaarxiv icon

High Fidelity Speech Synthesis with Adversarial Networks

Sep 26, 2019
Mikołaj Bińkowski, Jeff Donahue, Sander Dieleman, Aidan Clark, Erich Elsen, Norman Casagrande, Luis C. Cobo, Karen Simonyan

Figure 1 for High Fidelity Speech Synthesis with Adversarial Networks
Figure 2 for High Fidelity Speech Synthesis with Adversarial Networks
Figure 3 for High Fidelity Speech Synthesis with Adversarial Networks
Figure 4 for High Fidelity Speech Synthesis with Adversarial Networks
Viaarxiv icon

Robust Multi-channel Speech Recognition using Frequency Aligned Network

Feb 06, 2020
Taejin Park, Kenichi Kumatani, Minhua Wu, Shiva Sundaram

Figure 1 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 2 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 3 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Figure 4 for Robust Multi-channel Speech Recognition using Frequency Aligned Network
Viaarxiv icon

Sparsification via Compressed Sensing for Automatic Speech Recognition

Feb 09, 2021
Kai Zhen, Hieu Duy Nguyen, Feng-Ju Chang, Athanasios Mouchtaris, Ariya Rastrow, .

Figure 1 for Sparsification via Compressed Sensing for Automatic Speech Recognition
Figure 2 for Sparsification via Compressed Sensing for Automatic Speech Recognition
Figure 3 for Sparsification via Compressed Sensing for Automatic Speech Recognition
Figure 4 for Sparsification via Compressed Sensing for Automatic Speech Recognition
Viaarxiv icon

Toward Cross-Domain Speech Recognition with End-to-End Models

Mar 09, 2020
Thai-Son Nguyen, Sebastian Stüker, Alex Waibel

Figure 1 for Toward Cross-Domain Speech Recognition with End-to-End Models
Figure 2 for Toward Cross-Domain Speech Recognition with End-to-End Models
Figure 3 for Toward Cross-Domain Speech Recognition with End-to-End Models
Figure 4 for Toward Cross-Domain Speech Recognition with End-to-End Models
Viaarxiv icon

A survey on recently proposed activation functions for Deep Learning

Apr 07, 2022
Murilo Gustineli

Figure 1 for A survey on recently proposed activation functions for Deep Learning
Figure 2 for A survey on recently proposed activation functions for Deep Learning
Viaarxiv icon

Nonlinear predictive models computation in ADPCM schemes

Mar 03, 2022
Marcos Faundez-Zanuy

Figure 1 for Nonlinear predictive models computation in ADPCM schemes
Figure 2 for Nonlinear predictive models computation in ADPCM schemes
Figure 3 for Nonlinear predictive models computation in ADPCM schemes
Viaarxiv icon

Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks

Oct 09, 2021
Yashish M. Siriwardena, Chris Kitchen, Deanna L. Kelly, Carol Espy-Wilson

Figure 1 for Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks
Figure 2 for Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks
Figure 3 for Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks
Figure 4 for Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks
Viaarxiv icon

The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge

Mar 03, 2022
Juan M. Martín-Doñas, Aitor Álvarez

Figure 1 for The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge
Figure 2 for The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge
Figure 3 for The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge
Figure 4 for The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challenge
Viaarxiv icon

HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

Jun 10, 2020
Jiaqi Su, Zeyu Jin, Adam Finkelstein

Figure 1 for HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Figure 2 for HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Figure 3 for HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Figure 4 for HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
Viaarxiv icon