Search Results for author:
Found 35 papers, 2 papers with code
Improving Transformer-based Networks With Locality For Automatic Speaker Verification
The proposed models achieve 0. 75% EER on VoxCeleb 1 test set, outperforming the previously proposed Transformer-based models and CNN-based models, such as ResNet34 and ECAPA-TDNN.
Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation
Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting
In the context of keyword spotting (KWS), the replacement of handcrafted speech features by learnable features has not yielded superior KWS performance.
Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning
Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks.
Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
A comprehensive set of experiments are conducted to demonstrate that: 1) diverse acoustic environments do impact speaker recognition performance, which could advance research in audio forensics, 2) domain adversarial training learns the discriminative features which are also invariant to shifts between domains, 3) discrepancy-minimizing adaptation achieves effective performance simultaneously across multiple acoustic domains, and 4) moment-matching adaptation along with dynamic distribution alignment also significantly promotes speaker recognition performance on each domain, especially for the LENA-field domain with noise compared to all other systems.
Fearless Steps Challenge Phase-1 Evaluation Plan
The Fearless Steps Challenge 2019 Phase-1 (FSC-P1) is the inaugural Challenge of the Fearless Steps Initiative hosted by the Center for Robust Speech Systems (CRSS) at the University of Texas at Dallas.
Data-driven Attention and Data-independent DCT based Global Context Modeling for Text-independent Speaker Recognition
In this study, a general global time-frequency context modeling framework is proposed to leverage the context information specifically for speaker representation modeling.
Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning
In this study, we show that GAP is a special case of a discrete cosine transform (DCT) on time-frequency domain mathematically using only the lowest frequency component in frequency decomposition.
DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition
Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns.
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition
As such, we further propose a feature refinement loss for decorrelation to efficiently combine the set of input features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment
We show that fine-tuning with pseudo labels achieves a 5. 35% phoneme error rate reduction and 2. 48% MDD F1 score improvement over a labeled-samples-only fine-tuning baseline.
Impact of Naturalistic Field Acoustic Environments on Forensic Text-independent Speaker Verification System
Audio analysis for forensic speaker verification offers unique challenges in system performance due in part to data collected in naturalistic field acoustic environments where location/scenario uncertainty is common in the forensic data collection process.
Vision-Cloud Data Fusion for ADAS: A Lane Change Prediction Case Study
To advance the development of visual guidance systems, we introduce a novel vision-cloud data fusion methodology, integrating camera image and Digital Twin information from the cloud to help intelligent vehicles make better decisions.
Single-channel speech separation using Soft-minimum Permutation Invariant Training
A long-lasting problem in supervised speech separation is finding the correct label for each separated speech signal, referred to as label permutation ambiguity.
Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network
Most current speech technology systems are designed to operate well even in the presence of multiple active speakers.
Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora
With additional techniques such as pronunciation and silence probability modeling, plus multi-style training, we achieve a +5. 42% and +3. 18% relative WER improvement for the development and evaluation sets of the Fearless Steps Corpus.
DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning
Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field.
Respiratory Distress Detection from Telephone Speech using Acoustic and Prosodic Features
To capture these variations, we utilize a set of well-known acoustic and prosodic features with a Support Vector Machine (SVM) classifier for detecting the presence of respiratory distress.
Open-set Short Utterance Forensic Speaker Verification using Teacher-Student Network with Explicit Inductive Bias
In forensic applications, it is very common that only small naturalistic datasets consisting of short utterances in complex or unknown acoustic environments are available.
Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Forensic audio analysis for speaker verification offers unique challenges due to location/scenario uncertainty and diversity mismatch between reference and naturalistic field recordings.
Speaker Representation Learning using Global Context Guided Channel and Time-Frequency Transformations
In this study, we propose the global context guided channel and time-frequency transformations to model the long-range, non-local time-frequency dependencies and channel variances in speaker representations.
SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping
The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications.
Sensor Fusion of Camera and Cloud Digital Twin Information for Intelligent Vehicles
With the rapid development of intelligent vehicles and Advanced Driving Assistance Systems (ADAS), a mixed level of human driver engagements is involved in the transportation system.
Guided Generative Adversarial Neural Network for Representation Learning and High Fidelity Audio Generation using Fewer Labelled Audio Data
However, the model can become redundant if it is intended for a specific task.
A Unified Framework for Speech Separation
The initial solutions introduced for deep learning based speech separation analyzed the speech signals into time-frequency domain with STFT; and then encoded mixed signals were fed into a deep neural network based separator.
Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition
In the present study, we address this issue by investigating variants of large receptive field CNNs (LRF-CNNs) which include deeply recursive networks, dilated convolutional neural networks, and stacked hourglass networks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognition
An obvious approach to leverage data from a new domain (e. g., new accented speech) is to first generate a comprehensive dataset of all domains, by combining all available data, and then use this dataset to retrain the acoustic models.
Cross-lingual Text-independent Speaker Verification using Unsupervised Adversarial Discriminative Domain Adaptation
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data.
Probabilistic Permutation Invariant Training for Speech Separation
Recently proposed Permutation Invariant Training (PIT) addresses this problem by determining the output-label assignment which minimizes the separation error.
Convolutional Neural Network-based Speech Enhancement for Cochlear Implant Recipients
To improve speech enhancement methods for CI users, we propose to perform speech enhancement in a cochlear filter-bank feature space, a feature-set specifically designed for CI users based on CI auditory stimuli.
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfer
The best result, with a 0. 937 AUC score, was obtained with the proposed network.
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE).
Exploring OpenStreetMap Availability for Driving Environment Understanding
An intelligent vehicle should be able to understand the driver's perception of the environment as well as controlling behavior of the vehicle.
UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation
This document briefly describes the systems submitted by the Center for Robust Speech Systems (CRSS) from The University of Texas at Dallas (UTD) to the 2016 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE).
KU-ISPL Language Recognition System for NIST 2015 i-Vector Machine Learning Challenge
The experimental results show that the use of duration and score fusion improves language recognition performance by 5% relative in LRiMLC15 cost.
