Alert button

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

A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness

Dec 18, 2022
Tiantian Feng, Rajat Hebbar, Nicholas Mehlman, Xuan Shi, Aditya Kommineni, and Shrikanth Narayanan

Figure 1 for A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness
Figure 2 for A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness
Figure 3 for A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness
Figure 4 for A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness
Viaarxiv icon

Blind Signal Dereverberation for Machine Speech Recognition

Sep 30, 2022
Samik Sadhu, Hynek Hermansky

Figure 1 for Blind Signal Dereverberation for Machine Speech Recognition
Figure 2 for Blind Signal Dereverberation for Machine Speech Recognition
Figure 3 for Blind Signal Dereverberation for Machine Speech Recognition
Figure 4 for Blind Signal Dereverberation for Machine Speech Recognition
Viaarxiv icon

XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers

Oct 29, 2022
Roshan Sharma, Bhiksha Raj

Figure 1 for XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers
Figure 2 for XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers
Figure 3 for XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers
Figure 4 for XNOR-FORMER: Learning Accurate Approximations in Long Speech Transformers
Viaarxiv icon

MooseNet: A trainable metric for synthesized speech with plda backend

Jan 17, 2023
Ondřej Plátek, Ondřej Dušek

Figure 1 for MooseNet: A trainable metric for synthesized speech with plda backend
Figure 2 for MooseNet: A trainable metric for synthesized speech with plda backend
Viaarxiv icon

Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features

Dec 05, 2022
Tadipatri Uday Kiran Reddy, Sahukari Chaitanya Varun, Kota Pranav Kumar Sankala Sreekanth, Kodukula Sri Rama Murty

Figure 1 for Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features
Figure 2 for Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features
Figure 3 for Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features
Figure 4 for Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features
Viaarxiv icon

HMM-based data augmentation for E2E systems for building conversational speech synthesis systems

Dec 22, 2022
Ishika Gupta, Anusha Prakash, Jom Kuriakose, Hema A. Murthy

Figure 1 for HMM-based data augmentation for E2E systems for building conversational speech synthesis systems
Figure 2 for HMM-based data augmentation for E2E systems for building conversational speech synthesis systems
Figure 3 for HMM-based data augmentation for E2E systems for building conversational speech synthesis systems
Figure 4 for HMM-based data augmentation for E2E systems for building conversational speech synthesis systems
Viaarxiv icon

Breaking trade-offs in speech separation with sparsely-gated mixture of experts

Nov 11, 2022
Xiaofei Wang, Zhuo Chen, Yu Shi, Jian Wu, Naoyuki Kanda, Takuya Yoshioka

Figure 1 for Breaking trade-offs in speech separation with sparsely-gated mixture of experts
Figure 2 for Breaking trade-offs in speech separation with sparsely-gated mixture of experts
Figure 3 for Breaking trade-offs in speech separation with sparsely-gated mixture of experts
Viaarxiv icon

Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge

Apr 25, 2023
Chenpeng Du, Yiwei Guo, Feiyu Shen, Kai Yu

Figure 1 for Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge
Figure 2 for Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge
Viaarxiv icon

Source Free Domain Adaptation of a DNN for SSVEP-based Brain-Computer Interfaces

May 27, 2023
Osman Berke Guney, Deniz Kucukahmetler, Huseyin Ozkan

Figure 1 for Source Free Domain Adaptation of a DNN for SSVEP-based Brain-Computer Interfaces
Figure 2 for Source Free Domain Adaptation of a DNN for SSVEP-based Brain-Computer Interfaces
Figure 3 for Source Free Domain Adaptation of a DNN for SSVEP-based Brain-Computer Interfaces
Figure 4 for Source Free Domain Adaptation of a DNN for SSVEP-based Brain-Computer Interfaces
Viaarxiv icon

Continual Learning for On-Device Speech Recognition using Disentangled Conformers

Dec 13, 2022
Anuj Diwan, Ching-Feng Yeh, Wei-Ning Hsu, Paden Tomasello, Eunsol Choi, David Harwath, Abdelrahman Mohamed

Figure 1 for Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Figure 2 for Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Figure 3 for Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Figure 4 for Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Viaarxiv icon