27 Apr 2022
|
SERC
|
Institute for Infocomm Research
|
MFA: TDNN with Multi-Scale Frequency-Channel Attention for Text-Independent Speaker Verification with Short Utterances
|
Tianchi Liu,
Rohan Kumar Das,
Kong Aik Lee,
Haizhou Li
|
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
|
27 Apr 2022
|
SERC
|
Institute for Infocomm Research
|
Self-Supervised Speaker Recognition with Loss-Gated Learning
|
Ruijie Tao,
Kong Aik Lee,
Rohan Kumar Das,
Ville Hautamäki,
Haizhou Li
|
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
|
3 Feb 2022
|
SERC
|
Institute for Infocomm Research
|
PL-EESR: Perceptual Loss Based End-to-End Robust Speaker Representation Extraction
|
Yi Ma,
KONG AIK LEE,
Ville Hautamäki,
Haizhou Li
|
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
|
13 Jan 2022
|
SERC
|
Institute for Infocomm Research
|
Neural Acoustic-Phonetic Approach for Speaker Verification with Phonetic Attention Mask
|
Tianchi Liu,
Rohan Kumar Das,
KONG AIK LEE,
Haizhou Li
|
IEEE Signal Processing Letters
|
30 Aug 2021
|
SERC
|
Institute for Infocomm Research
|
Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
|
Hongning Zhu,
KONG AIK LEE,
Haizhou Li
|
Interspeech 2021
|
30 Aug 2021
|
SERC
|
Institute for Infocomm Research
|
Multi-Level Transfer Learning from Near-Field to Far-Field Speaker Verification
|
Li Zhang,
Qing Wang,
KONG AIK LEE,
Lei Xie,
Haizhou Li
|
Interspeech 2021
|
29 Jul 2021
|
SERC
|
Institute for Infocomm Research
|
Multi-Tone Phase Coding of Interaural Time Difference for Sound Source Localization With Spiking Neural Networks
|
Zihan Pan,
Malu Zhang,
Jibin Wu,
Jiadong Wang,
Haizhou Li
|
IEEE/ACM Transactions on Audio, Speech, and Language Processing
|
7 May 2021
|
SERC
|
Institute for Infocomm Research
|
The Psychoacoustics and Synthesis of Singing Harmony
|
Paul Yaozhu Chan,
Minghui Dong,
Haizhou Li
|
Digital Repository of NTU
|
7 May 2021
|
SERC
|
Institute for Infocomm Research
|
Deep Bidirectional LSTM Modeling of Timbre and Prosody for Emotional Voice Conversion
|
Huaiping Ming,
Dongyan Huang,
Lei Xie,
Jie Wu,
Minghui Dong,
Haizhou Li
|
Interspeech 2016
|
20 Feb 2020
|
SERC
|
Institute for Infocomm Research
|
On the Study of Generative Adversarial Networks for Cross-Lingual Voice Conversion
|
Berrak Sisman,
MIngyang Zhang,
Minghui Dong,
Haizhou Li
|
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
|
29 Sep 2019
|
SERC
|
Institute for Infocomm Research
|
The Science of Harmony: A Psychophysical Basis for Perceptual Tensions and Resolutions in Music
|
Paul Yaozhu Chan,
Minghui Dong,
Haizhou Li
|
Research
|
20 Jul 2018
|
SERC
|
Institute for Infocomm Research
|
Named-Entity Tagging and Domain adaptation for Better Customized Translation
|
Zhongwei Li,
Xuancong Wang,
Ai Ti Ai,
Eng Siong Chng,
Haizhou Li
|
Proceedings of the Seventh Named Entities Workshop 2018
|
18 Apr 2018
|
SERC
|
Institute for Infocomm Research
|
ON THE IMPORTANCE OF ANALYTIC PHASE OF SPEECH SIGNALS IN SPOKEN LANGUAGE RECOGNITION
|
Karthika Vijayan,
Haizhou Li,
Hanwu Sun
|
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018)
|
16 Dec 2017
|
SERC
|
Institute for Infocomm Research
|
Multilingual Bottle-Neck Feature Learning from Untranscribed Speech
|
Hongjie Chen,
Cheung-Chi Leung,
Lei Xie,
Bin Ma,
Haizhou Li
|
ASRU 2017
|
16 Dec 2017
|
SERC
|
Institute for Infocomm Research
|
Extracting Bottleneck Features and Word-Like Pairs from Untranscribed Speech for Feature Representation
|
Yougen Yuan,
Cheung-Chi Leung,
Lei Xie,
Hongjie Chen,
Bin Ma,
Haizhou Li
|
ASRU 2017
|
12 Dec 2017
|
SERC
|
Institute for Infocomm Research
|
I2R-NUS Submission to Oriental Language Recognition AP16-OL7 Challenge
|
Hanwu Sun,
KONG AIK LEE,
Trung Hieu Nguyen,
Bin Ma,
Haizhou Li
|
Asia-Pacific Signal and Information Processing Association (APSIPA) Regional Conference (2017)
|
18 Oct 2017
|
SERC
|
Institute for Infocomm Research
|
Multi-Task Feature Learning for Low-Resource Query-by-Example Spoken Term Detection
|
Bin Ma,
Haizhou Li,
Hongjie Chen,
Cheung-Chi Leung,
Lei Xie
|
IEEE Journal of Selected Topics in Signal Processing
|
8 Sep 2016
|
SERC
|
Institute for Infocomm Research
|
Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis
|
Cheung-Chi Leung,
Lei Wang,
Haihua Xu,
Jingyong Hou,
Tung Pham Van,
Hang Lv,
Lei Xie,
Xiong Xiao,
Chongjia Ni,
Bin Ma,
Eng Siong Chng,
Haizhou Li
|
INTERSPEECH 2016
|
8 Sep 2016
|
SERC
|
Institute for Infocomm Research
|
Rapid Update of Multilingual Deep Neural Network for Low-Resource Keyword Search
|
Chongjia Ni,
Lei Wang,
Cheung Chi Leung,
Feng Rao,
Li Lu,
Bin Ma,
Haizhou Li
|
INTERSPEECH 2016
|
8 Apr 2016
|
SERC
|
Institute for Infocomm Research
|
How the Brain Formulates Memory: A Spatio-Temporal Model
|
Huajin Tang,
Jun Hu,
Kay Chen Tan,
Haizhou Li
|
IEEE Computational intelligence magazine
|
24 Oct 2015
|
SERC
|
Institute for Infocomm Research
|
Joint Chinese word segmentation and punctuation prediction using deep recurrent neural network for social media data
|
Haizhou Li,
Nina Zhou,
AiTi Aw,
Kui Wu,
Xuancong Wang
|
2015 International Conference on Asian Language Processing (IALP)
|
13 Oct 2015
|
SERC
|
Institute for Infocomm Research
|
Octave-dependent Probabilistic Latent Semantic Analysis to Chorus Detection of Popular Song
|
Sheng Gao,
Haizhou Li
|
MM '15 Proceedings of the 23rd ACM international conference on Multimedia
|
17 Sep 2015
|
SERC
|
Institute for Infocomm Research
|
Wikification of Concept Mentions within Spoken Dialogues Using Domain Constraints from Wikipedia
|
Haizhou Li,
Rafael E. Banchs,
Seokhwan Kim
|
Conference on Empirical Methods in Natural Language Processing (EMNLP)
|
2 Sep 2015
|
SERC
|
Institute for Infocomm Research
|
Towards Improving Dialogue Topic Tracking Performances with Wikification of Concept Mentions
|
Seokhwan Kim,
Rafael E. Banchs,
Haizhou Li
|
Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)
|
14 Sep 2014
|
SERC
|
Institute for Infocomm Research
|
I2R Speech2Singing Perfects Everyone’s Singing
|
Minghui Dong,
Siu Wa Lee,
Haizhou Li,
Paul Yaozhu Chan,
Xuejian Peng,
Jochen Walter Ehnes,
Dongyan Huang
|
|
22 Jun 2014
|
SERC
|
Institute for Infocomm Research
|
A Composite Kernel Approach for Dialog Topic Tracking with Structured Domain Knowledge from Wikipedia
|
Seokhwan Kim,
Rafael E. Banchs,
Haizhou Li
|
Annual Meeting of the Association for Computational Linguistics (ACL)
|
4 May 2014
|
SERC
|
Institute for Infocomm Research
|
Wikipedia-based Kernels for dialogue topic tracking
|
Seokhwan Kim,
Rafael E. Banchs,
Haizhou Li
|
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
|
1 Sep 2013
|
SERC
|
Institute for Infocomm Research
|
Spoken Language Recognition with Prosodic Features
|
Raymond W. M. Ng,
Tan Lee,
Cheung-Chi Leung,
Bin Ma,
Haizhou Li
|
IEEE Transctions on Audio, Speech, and Language Processing
|
28 Aug 2013
|
SERC
|
Institute for Infocomm Research
|
Graph-based Informative-Sentence Selection for Opinion Summarization
|
Linhong Zhu,
Jialin Sinno Pan,
Sheng Gao,
Haizhou Li,
Dingxiong Deng
|
2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
|
25 Aug 2013
|
SERC
|
Institute for Infocomm Research
|
Unsupervised Mining of Acoustic Subword Units with Segment-Level Gaussian Posteriorgrams
|
Haipeng Wang,
Tan Lee,
Cheung-Chi Leung,
Bin Ma,
Haizhou Li
|
|
9 Aug 2013
|
SERC
|
Institute for Infocomm Research
|
An Attention-Directed Robot for Social Telepresence (Pending publish)
|
Rui Yan,
Keng Peng Tee,
Yuanwei Chua,
Zhiyong Huang,
Haizhou Li
|
|
4 Aug 2013
|
SERC
|
Institute for Infocomm Research
|
Broadcast News Story Segmentation Using Manifold Learning on Latent Topic Distributions
|
Lei Xie,
Cheung-Chi Leung,
Bin Ma,
Haizhou Li,
Xiaoming Lu
|
|
1 Aug 2013
|
SERC
|
Institute for Infocomm Research
|
Sparse Classifier Fusion for Speaker Verification (Pending publish)
|
KONG AIK LEE,
Bin Ma,
Haizhou Li,
Ville Hautamäki,
Tomi Kinnunen,
Filip Sedlák
|
IEEE Transactions on Audio, Speech and Language Processing
|