Alert button
Picture for Andrew Hines

Andrew Hines

Alert button

NOMAD: Unsupervised Learning of Perceptual Embeddings for Speech Enhancement and Non-matching Reference Audio Quality Assessment

Sep 28, 2023
Alessandro Ragano, Jan Skoglund, Andrew Hines

Viaarxiv icon

Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models

Sep 22, 2023
Asad Ullah, Alessandro Ragano, Andrew Hines

Figure 1 for Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models
Figure 2 for Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models
Figure 3 for Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models
Figure 4 for Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models
Viaarxiv icon

Exploring the Impact of Noise and Degradations on Heart Sound Classification Models

Nov 14, 2022
Davoud Shariat Panah, Andrew Hines, Susan McKeever

Figure 1 for Exploring the Impact of Noise and Degradations on Heart Sound Classification Models
Figure 2 for Exploring the Impact of Noise and Degradations on Heart Sound Classification Models
Figure 3 for Exploring the Impact of Noise and Degradations on Heart Sound Classification Models
Figure 4 for Exploring the Impact of Noise and Degradations on Heart Sound Classification Models
Viaarxiv icon

Learning Music Representations with wav2vec 2.0

Oct 27, 2022
Alessandro Ragano, Emmanouil Benetos, Andrew Hines

Figure 1 for Learning Music Representations with wav2vec 2.0
Figure 2 for Learning Music Representations with wav2vec 2.0
Figure 3 for Learning Music Representations with wav2vec 2.0
Figure 4 for Learning Music Representations with wav2vec 2.0
Viaarxiv icon

Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset

Sep 14, 2022
Michael Chinen, Jan Skoglund, Chandan K A Reddy, Alessandro Ragano, Andrew Hines

Figure 1 for Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
Figure 2 for Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
Figure 3 for Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
Viaarxiv icon

A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality

Apr 05, 2022
Alessandro Ragano, Emmanouil Benetos, Michael Chinen, Helard B. Martinez, Chandan K. A. Reddy, Jan Skoglund, Andrew Hines

Figure 1 for A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality
Figure 2 for A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality
Figure 3 for A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality
Figure 4 for A Comparison of Deep Learning MOS Predictors for Speech Synthesis Quality
Viaarxiv icon

Exploring the influence of fine-tuning data on wav2vec 2.0 model for blind speech quality prediction

Apr 05, 2022
Helard Becerra, Alessandro Ragano, Andrew Hines

Figure 1 for Exploring the influence of fine-tuning data on wav2vec 2.0 model for blind speech quality prediction
Figure 2 for Exploring the influence of fine-tuning data on wav2vec 2.0 model for blind speech quality prediction
Figure 3 for Exploring the influence of fine-tuning data on wav2vec 2.0 model for blind speech quality prediction
Viaarxiv icon

AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics

Oct 26, 2021
Jack Geraghty, Jiazheng Li, Alessandro Ragano, Andrew Hines

Figure 1 for AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics
Figure 2 for AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics
Figure 3 for AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics
Viaarxiv icon

More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations

Aug 19, 2021
Alessandro Ragano, Emmanouil Benetos, Andrew Hines

Figure 1 for More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations
Figure 2 for More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations
Figure 3 for More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations
Figure 4 for More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations
Viaarxiv icon

WARP-Q: Quality Prediction For Generative Neural Speech Codecs

Feb 20, 2021
Wissam A. Jassim, Jan Skoglund, Michael Chinen, Andrew Hines

Figure 1 for WARP-Q: Quality Prediction For Generative Neural Speech Codecs
Figure 2 for WARP-Q: Quality Prediction For Generative Neural Speech Codecs
Figure 3 for WARP-Q: Quality Prediction For Generative Neural Speech Codecs
Figure 4 for WARP-Q: Quality Prediction For Generative Neural Speech Codecs
Viaarxiv icon