Alert button
Picture for Xiaoxiao Miao

Xiaoxiao Miao

Alert button

Speaker-Text Retrieval via Contrastive Learning

Dec 11, 2023
Xuechen Liu, Xin Wang, Erica Cooper, Xiaoxiao Miao, Junichi Yamagishi

Viaarxiv icon

VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research

Sep 14, 2023
Sarina Meyer, Xiaoxiao Miao, Ngoc Thang Vu

Figure 1 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 2 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 3 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Figure 4 for VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Research
Viaarxiv icon

SynVox2: Towards a privacy-friendly VoxCeleb2 dataset

Sep 12, 2023
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Nicholas Evans, Massimiliano Todisco, Jean-François Bonastre, Mickael Rouvier

Figure 1 for SynVox2: Towards a privacy-friendly VoxCeleb2 dataset
Figure 2 for SynVox2: Towards a privacy-friendly VoxCeleb2 dataset
Figure 3 for SynVox2: Towards a privacy-friendly VoxCeleb2 dataset
Figure 4 for SynVox2: Towards a privacy-friendly VoxCeleb2 dataset
Viaarxiv icon

Language-independent speaker anonymization using orthogonal Householder neural network

May 30, 2023
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko

Figure 1 for Language-independent speaker anonymization using orthogonal Householder neural network
Figure 2 for Language-independent speaker anonymization using orthogonal Householder neural network
Figure 3 for Language-independent speaker anonymization using orthogonal Householder neural network
Figure 4 for Language-independent speaker anonymization using orthogonal Householder neural network
Viaarxiv icon

Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms

May 18, 2023
Chang Zeng, Xin Wang, Xiaoxiao Miao, Erica Cooper, Junichi Yamagishi

Figure 1 for Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
Figure 2 for Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
Figure 3 for Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
Figure 4 for Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms
Viaarxiv icon

Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline

Nov 29, 2022
Paul-Gauthier Noé, Xiaoxiao Miao, Xin Wang, Junichi Yamagishi, Jean-François Bonastre, Driss Matrouf

Figure 1 for Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline
Figure 2 for Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline
Figure 3 for Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline
Figure 4 for Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline
Viaarxiv icon

The VoicePrivacy 2022 Challenge Evaluation Plan

Mar 27, 2022
Natalia Tomashenko, Xin Wang, Xiaoxiao Miao, Hubert Nourtel, Pierre Champion, Massimiliano Todisco, Emmanuel Vincent, Nicholas Evans, Junichi Yamagishi, Jean-François Bonastre

Figure 1 for The VoicePrivacy 2022 Challenge Evaluation Plan
Figure 2 for The VoicePrivacy 2022 Challenge Evaluation Plan
Figure 3 for The VoicePrivacy 2022 Challenge Evaluation Plan
Figure 4 for The VoicePrivacy 2022 Challenge Evaluation Plan
Viaarxiv icon

Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models

Mar 26, 2022
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Natalia Tomashenko

Figure 1 for Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models
Figure 2 for Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models
Figure 3 for Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models
Figure 4 for Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models
Viaarxiv icon

LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge

Dec 19, 2019
Xiaoxiao Miao, Ian McLoughlin

Figure 1 for LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge
Figure 2 for LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge
Figure 3 for LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge
Figure 4 for LSTM-TDNN with convolutional front-end for Dialect Identification in the 2019 Multi-Genre Broadcast Challenge
Viaarxiv icon