research
∙
05/03/2022
Attentive activation function for improving end-to-end spoofing countermeasure systems
The main objective of the spoofing countermeasure system is to detect th...
share
research
∙
12/07/2021
Robust Speech Representation Learning via Flow-based Embedding Regularization
Over the recent years, various deep learning-based methods were proposed...
research
∙
02/06/2021
Continuous Monitoring of Blood Pressure with Evidential Regression
Photoplethysmogram (PPG) signal-based blood pressure (BP) estimation is ...
research
∙
10/22/2020
Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning
In this paper, we propose a simple but powerful unsupervised learning me...
research
∙
10/22/2020
Robust Text-Dependent Speaker Verification via Character-Level Information Preservation for the SdSV Challenge 2020
This paper describes our submission to Task 1 of the Short-duration Spea...
research
∙
08/07/2020
Disentangled speaker and nuisance attribute embedding for robust speaker verification
Over the recent years, various deep learning-based embedding methods hav...
research
∙
07/25/2020
Robust Front-End for Multi-Channel ASR using Flow-Based Density Estimation
For multi-channel speech recognition, speech enhancement techniques such...
research
∙
07/10/2020
Gated Recurrent Context: Softmax-free Attention for Online Encoder-Decoder Speech Recognition
Recently, attention-based encoder-decoder (AED) models have shown state-...
research
∙
06/08/2020
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
Flow-based generative models are composed of invertible transformations ...
research
∙
06/08/2020
WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
In recent years, various flow-based generative models have been proposed...
research
∙
10/21/2019
Disambiguating Speech Intention via Audio-Text Co-attention Framework: A Case of Prosody-semantics Interface
Understanding the intention of an utterance is challenging for some pros...
research
∙
10/31/2018
Real-time Automatic Word Segmentation for User-generated Text
For readability and possibly for disambiguation, appropriate word segmen...
research
∙
10/10/2018