39 citations · 132 across the 28 of their papers we have counts for
29 papers
Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language
Turi Abu, Ying Shi, Thomas Fang Zheng +1
We present a novel Automatic Speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected throug…
How Speech is Recognized to Be Emotional - A Study Based on Information Decomposition
Haoran Sun, Lantian Li, Thomas Fang Zheng +1
The way that humans encode their emotion into speech signals is complex. For instance, an angry man may increase his pitch and speaking rate, and use impolite words. In this paper,…
A Multi-Resolution Front-End for End-to-End Speech Anti-Spoofing
Wei Liu, Meng Sun, Xiongwei Zhang +2
The choice of an optimal time-frequency resolution is usually a difficult but important step in tasks involving speech signal classification, e.g., speech anti-spoofing. The variat…
Attack on practical speaker verification system using universal adversarial perturbations
Weiyi Zhang, Shuning Zhao, Le Liu +4
In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text. Previous studies played an audio…
CN-Celeb: multi-genre speaker recognition
Lantian Li, Ruiqi Liu, Jiawen Kang +6
Research on speaker recognition is extending to address the vulnerability in the wild conditions, among which genre mismatch is perhaps the most challenging, for instance, enrollme…
Squeezing value of cross-domain labels: a decoupled scoring approach for speaker verification
Lantian Li, Yang Zhang, Jiawen Kang +2
Domain mismatch often occurs in real applications and causes serious performance reduction on speaker verification systems. The common wisdom is to collect cross-domain data and tr…
Deep generative factorization for speech signal
Haoran Sun, Lantian Li, Yunqi Cai +3
Various information factors are blended in speech signals, which forms the primary difficulty for most speech information processing tasks. An intuitive idea is to factorize speech…
When Automatic Voice Disguise Meets Automatic Speaker Verification
Linlin Zheng, Jiakang Li, Meng Sun +2
The technique of transforming voices in order to hide the real identity of a speaker is called voice disguise, among which automatic voice disguise (AVD) by modifying the spectral…
Neural Discriminant Analysis for Deep Speaker Embedding
Lantian Li, Dong Wang, Thomas Fang Zheng
Probabilistic Linear Discriminant Analysis (PLDA) is a popular tool in open-set classification/verification tasks. However, the Gaussian assumption underlying PLDA prevents it from…
ASR-Free Pronunciation Assessment
Sitong Cheng, Zhixin Liu, Lantian Li +3
Most of the pronunciation assessment methods are based on local features derived from automatic speech recognition (ASR), e.g., the Goodness of Pronunciation (GOP) score. In this p…
Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
Jiawen Kang, Ruiqi Liu, Lantian Li +3
Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets. For example, a model trained on re…
RACORN-K: Risk-Aversion Pattern Matching-based Portfolio Selection
Yang Wang, Dong Wang, Yaodong Wang +1
Portfolio selection is the central task for assets management, but it turns out to be very challenging. Methods based on pattern matching, particularly the CORN-K algorithm, have a…
Full-info Training for Deep Speaker Feature Learning
Lantian Li, Zhiyuan Tang, Dong Wang +1
In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neu…
Enhanced Neural Machine Translation by Learning from Draft
Aodong Li, Shiyue Zhang, Dong Wang +1
Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left t…
Cross-lingual Speaker Verification with Deep Feature Learning
Lantian Li, Dong Wang, Askar Rozi +1
Existing speaker verification (SV) systems often suffer from performance degradation if there is any language mismatch between model training, speaker enrollment, and test. A major…
Deep Speaker Verification: Do We Need End to End?
Dong Wang, Lantian Li, Zhiyuan Tang +1
End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. T…
A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification
Lantian Li, Yixiang Chen, Dong Wang +1
For practical automatic speaker verification (ASV) systems, replay attack poses a true risk. By replaying a pre-recorded speech signal of the genuine speaker, ASV systems tend to b…
Decision Making Based on Cohort Scores for Speaker Verification
Lantian Li, Renyu Wang, Gang Wang +2
Decision making is an important component in a speaker verification system. For the conventional GMM-UBM architecture, the decision is usually conducted based on the log likelihood…
System Combination for Short Utterance Speaker Recognition
Lantian Li, Dong Wang, Xiaodong Zhang +2
For text-independent short-utterance speaker recognition (SUSR), the performance often degrades dramatically. This paper presents a combination approach to the SUSR tasks with two…
Transfer Learning for Speech and Language Processing
Dong Wang, Thomas Fang Zheng
Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trai…
Max-margin Metric Learning for Speaker Recognition
Lantian Li, Dong Wang, Chao Xing +1
Probabilistic linear discriminant analysis (PLDA) is a popular normalization approach for the i-vector model, and has delivered state-of-the-art performance in speaker recognition.…
Binary Speaker Embedding
Lantian Li, Dong Wang, Chao Xing +2
The popular i-vector model represents speakers as low-dimensional continuous vectors (i-vectors), and hence it is a way of continuous speaker embedding. In this paper, we investiga…
Parallel Knowledge Embedding with MapReduce on a Multi-core Processor
Miao Fan, Qiang Zhou, Thomas Fang Zheng +1
This article firstly attempts to explore parallel algorithms of learning distributed representations for both entities and relations in large-scale knowledge repositories with {\it…
Deep Speaker Vectors for Semi Text-independent Speaker Verification
Lantian Li, Dong Wang, Zhiyong Zhang +1
Recent research shows that deep neural networks (DNNs) can be used to extract deep speaker vectors (d-vectors) that preserve speaker characteristics and can be used in speaker veri…