LSTM Based End-to-End Text-Independent Speaker Verification Using Raw Waveform

He, Jing; Zhang, Pengwei; Zhu, Liangjin

doi:10.1109/iccst50977.2020.00103

“…Automatic Speaker Veri cation (ASV) is the process of identifying the speaker's unknown utterances in the registered voice database. Recently, inspired by the boom of computer calculating power, robust feature extraction capabilities of deep neural networks were demonstrated and evolved many network structure, which is rooted essentially at DNN [1], RNN/LSTM [2], and CNN [3] [4]. The CNN [5] excels at identifying patterns in the input and can scale much better than DNN.…”

Section: Introductionmentioning

confidence: 99%

Speaker verification based on 3D variational self-coding multi-tasking adversarial network

Liao

¹

,

Xue

²

2022

Preprint

0

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

show abstract

Speaker Verification: A Raw Waveform Approach for Text Independent using CNN

Paranatti

¹

,

Bhandari

²

,

Patil

³

et al. 2024

2024 3rd International Conference for Innovation in Technology (INOCON)

1

0

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

Multi-domain Acoustic Feature Fusion for Speaker Recognition

Yao

¹

,

Li

²

2024

Proceedings of the 6th ACM International Conference on Multimedia in Asia

0

Get access via publisher Add to dashboard Cite

Exaggerated anticipatory anxiety is common in social anxiety disorder (SAD). Neuroimaging studies have revealed altered neural activity in response to social stimuli in SAD, but fewer studies have examined neural activity during anticipation of feared social stimuli in SAD. The current study examined the time course and magnitude of activity in threat processing brain regions during speech anticipation in socially anxious individuals and healthy controls (HC). Method Participants (SAD n = 58; HC n = 16) underwent functional magnetic resonance imaging (fMRI) during which they completed a 90s control anticipation task and 90s speech anticipation task.

LSTM Based End-to-End Text-Independent Speaker Verification Using Raw Waveform

Cited by 3 publications

References 11 publications

Speaker verification based on 3D variational self-coding multi-tasking adversarial network

Speaker verification based on 3D variational self-coding multi-tasking adversarial network

Speaker Verification: A Raw Waveform Approach for Text Independent using CNN

Multi-domain Acoustic Feature Fusion for Speaker Recognition

Contact Info

Product

Resources

About