Thanh Do

Mr. Thanh Do

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 March 2022 in Signal Processing
Verified
Journal Article
Closed access
TDThanh Do
Thanh Do
TNTran Thien Dat Nguyen
Tran Thien Dat Nguyen
DMDiluka Moratuwage
Diluka Moratuwage
CSChangbeom Shim
Changbeom Shim
YCYon Dohn Chung
Yon Dohn Chung

8 April 2019 in Sensors
Verified
Journal Article
Open access
PDF file
TDThanh Do
Thanh Do
HNHoa Nguyen
Hoa Nguyen
The measurements from multistatic radar systems are typically subjected to complicated data association, noise corruption, missed detection, and false alarms. Moreover, most of the current multistatic Doppler radar-based approaches in multitarget tracking are based on the assumption of known detection probability. This assumption can lead to biased or even complete corruption of estimation results. This paper proposes a method for tracking multiple targets from multistatic Doppler radar with unknown detection probability. A closed form labeled multitarget Bayes filter was used to track unknown and time-varying targets with unknown probability of detection in the presence of clutter, misdetection, and association uncertainty. The efficiency of the proposed algorithm was illustrated via numerical simulation examples.

18 November 2019 in Sensors
Verified
Journal Article
Open access
PDF file
TDThanh Do
Thanh Do
TNTran Thien Dat Nguyen
Tran Thien Dat Nguyen
WLWeifeng Liu
Weifeng Liu
In multitarget tracking, knowledge of the backgrounds plays a crucial role in the accuracy of the tracker. Clutter and detection probability are the two essential background parameters which are usually assumed to be known constants although they are, in fact, unknown and time varying. Incorrect values of these parameters lead to a degraded or biased performance of the tracking algorithms. This paper proposes a method for online tracking multiple targets using multiple sensors which jointly adapts to the unknown clutter rate and the probability of detection. An effective filter is developed from parallel estimation of these parameters and then feeding them into the state-of-the-art generalized labeled multi-Bernoulli filter. Provided that the fluctuation of these unknown backgrounds is slowly-varying in comparison to the rate of measurement-update data, the validity of the proposed method is demonstrated via numerical study using multistatic Doppler data.

6 June 2021
Verified
Conference Paper
Open access
TDThanh Do
Thanh Do
RDRama Doddipatla
Rama Doddipatla
THThomas Hain
Thomas Hain
This paper proposes an adaptation method for end-to-end speech recognition. In this method, multiple automatic speech recognition (ASR) 1-best hypotheses are integrated in the computation of the connectionist temporal classification (CTC) loss function. The integration of multiple ASR hypotheses helps alleviating the impact of errors in the ASR hypotheses to the computation of the CTC loss when ASR hypotheses are used. When being applied in semi-supervised adaptation scenarios where part of the adaptation data do not have labels, the CTC loss of the proposed method is computed from different ASR 1-best hypotheses obtained by decoding the unlabeled adaptation data. Experiments are performed in clean and multi-condition training scenarios where the CTC-based end-to-end ASR systems are trained on Wall Street Journal (WSJ) clean training data and CHiME-4 multi-condition training data, respectively, and tested on Aurora-4 test data. The proposed adaptation method yields 6.6% and 5.8% relative word error rate (WER) reductions in clean and multi-condition training scenarios, respectively, compared to a baseline system which is adapted with part of the adaptation data having manual transcriptions using back-propagation fine-tuning.

6 June 2021
Verified
Conference Paper
Open access
SZShucong Zhang
Shucong Zhang
TDThanh Do
Thanh Do
RDRama Doddipatla
Rama Doddipatla
ELErfan Loweimi
Erfan Loweimi
PBPeter Bell
Peter Bell
SRSteve Renals
Steve Renals
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in general, freezing the trained feature extractor (the lower layers) and retraining the classifier (the upper layers) on the same dataset leads to worse performance. In this paper, for the first time, we show that the frozen classifier is transferable within the same dataset. We develop a novel top-down training method which can be viewed as an algorithm for searching for high-quality classifiers. We tested this method on automatic speech recognition (ASR) tasks and language modelling tasks. The proposed method consistently improves recurrent neural network ASR models on Wall Street Journal, self-attention ASR models on Switchboard, and AWD-LSTM language models on WikiText-2.

1 October 2019
Verified
Conference Paper
Closed access
TDThanh Do
Thanh Do
TNTran Thien Dat Nguyen
Tran Thien Dat Nguyen
The data collected by a multi static Doppler radar system includes information on both true targets and clutter. The estimation of clutter directly influences the effectiveness of the multitarget tracker in practical applications. This paper proposes a method for tracking multiple marine ships using multistatic Doppler radar system in an environment with unknown clutter rate. Specifically, the clutter rate is first estimated and then bootstrapped into the state-of-the-art Vo- Vo filter to track multiple targets on-the-fly. Numerical results demonstrate the validity of the proposed method provide that the clutter parameter vary slower than that of the data.