Cong-Thanh Do

Objective evaluation of HMM-based speech synthesis system using kullback-leibler divergence

Christophe d'Alessandro, Albert Rilliard, Cong-Thanh Do, 2014, INTERSPEECH.

A novel framework for noise robust ASR using cochlear implant-like spectrally reduced speech

Dominique Pastor, Cong-Thanh Do, André Goalic, 2012, Speech Commun..

Tracking Multiple Marine Ships via Multiple Sensors with Unknown Backgrounds

Weifeng Liu, Cong-Thanh Do, Tran Thien Dat Nguyen, 2019, Sensors.

Weighting Time-Frequency Representation of Speech Using Auditory Saliency for Automatic Speech Recognition

Yannis Stylianou, Cong-Thanh Do, Y. Stylianou, 2018, INTERSPEECH.

Improved Automatic Speech Recognition Using Subband Temporal Envelope Features and Time-Delay Neural Network Denoising Autoencoder

Yannis Stylianou, Cong-Thanh Do, Y. Stylianou, 2017, INTERSPEECH.

Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer

Rama Doddipatla, Cong-Thanh Do, Mohan Li, 2022, INTERSPEECH.

Robust Multi-Sensor Generalized Labeled Multi-Bernoulli Filter

Hoa Van Nguyen, Cong-Thanh Do, Tran Thien Dat Nguyen, 2021, Signal Processing.

Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition

Steve Renals, Shucong Zhang, Cong-Thanh Do, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Combination of Cepstral and Phonetically Discriminative Features for Speaker Verification

Claude Barras, Achintya Kumar Sarkar, Viet Bac Le, 2014, IEEE Signal Processing Letters.

Cumulative Attention Based Streaming Transformer ASR with Internal Language Model Joint Training and Rescoring

Cong-Thanh Do, Mohan Li, R. Doddipatla, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Train Your Classifier First: Cascade Neural Networks Training from Upper Layers to Lower Layers

Peter Bell, Steve Renals, Erfan Loweimi, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis

Cong-Thanh Do, R. Doddipatla, Shuhei Imai, 2024, 2407.04047.