Alert button
Picture for Amber Afshan

Amber Afshan

Alert button

Learning from human perception to improve automatic speaker verification in style-mismatched conditions

Jun 28, 2022
Amber Afshan, Abeer Alwan

Figure 1 for Learning from human perception to improve automatic speaker verification in style-mismatched conditions
Figure 2 for Learning from human perception to improve automatic speaker verification in style-mismatched conditions
Figure 3 for Learning from human perception to improve automatic speaker verification in style-mismatched conditions
Viaarxiv icon

Attention-based conditioning methods using variable frame rate for style-robust speaker verification

Jun 28, 2022
Amber Afshan, Abeer Alwan

Figure 1 for Attention-based conditioning methods using variable frame rate for style-robust speaker verification
Figure 2 for Attention-based conditioning methods using variable frame rate for style-robust speaker verification
Figure 3 for Attention-based conditioning methods using variable frame rate for style-robust speaker verification
Viaarxiv icon

Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models

Jun 30, 2021
Amber Afshan, Kshitiz Kumar, Jian Wu

Figure 1 for Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
Figure 2 for Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
Figure 3 for Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
Figure 4 for Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
Viaarxiv icon

Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR

Feb 12, 2021
Ruchao Fan, Amber Afshan, Abeer Alwan

Figure 1 for Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
Figure 2 for Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
Figure 3 for Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
Figure 4 for Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR
Viaarxiv icon

Speaker discrimination in humans and machines: Effects of speaking style variability

Aug 08, 2020
Amber Afshan, Jody Kreiman, Abeer Alwan

Figure 1 for Speaker discrimination in humans and machines: Effects of speaking style variability
Figure 2 for Speaker discrimination in humans and machines: Effects of speaking style variability
Figure 3 for Speaker discrimination in humans and machines: Effects of speaking style variability
Viaarxiv icon

Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification

Aug 08, 2020
Amber Afshan, Jinxi Guo, Soo Jin Park, Vijay Ravi, Alan McCree, Abeer Alwan

Figure 1 for Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification
Figure 2 for Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification
Figure 3 for Variable frame rate-based data augmentation to handle speaking-style variability for automatic speaker verification
Viaarxiv icon

Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification

Aug 08, 2020
Vijay Ravi, Ruchao Fan, Amber Afshan, Huanhua Lu, Abeer Alwan

Figure 1 for Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification
Figure 2 for Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification
Figure 3 for Exploring the Use of an Unsupervised Autoregressive Model as a Shared Encoder for Text-Dependent Speaker Verification
Viaarxiv icon