S
Songxiang Liu
Researcher at The Chinese University of Hong Kong
Publications - 44
Citations - 564
Songxiang Liu is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 9, co-authored 35 publications receiving 276 citations. Previous affiliations of Songxiang Liu include Tencent.
Papers
More filters
Proceedings ArticleDOI
Speech Emotion Recognition Using Capsule Networks
Xixin Wu,Songxiang Liu,Yuewen Cao,Xu Li,Jianwei Yu,Dongyang Dai,Xi Ma,Shoukang Hu,Zhiyong Wu,Xunying Liu,Helen Meng +10 more
TL;DR: This paper presents a novel architecture based on the capsule networks (CapsNets) for SER that can take into account the spatial relationship of speech features in spectrograms, and provide an effective pooling method for obtaining utterance global features.
Proceedings ArticleDOI
Voice Conversion Across Arbitrary Speakers Based on a Single Target-Speaker Utterance.
TL;DR: The i-vector-based VC (IVC) approach is superior to SEVC, in terms of the quality of the converted speech and its similarity to the utterance produced by the genuine target speaker.
Posted Content
Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification
TL;DR: In this paper, the authors investigate the vulnerability of spoofing countermeasures for ASV under both white-box and black-box adversarial attacks with the fast gradient sign method (FGSM) and the projected gradient descent (PGD) method.
Proceedings ArticleDOI
End-to-end Code-switched TTS with Mix of Monolingual Recordings
TL;DR: The proposed E2E TTS systems can generate controllable foreign-accented speech at character-level using only mixture of monolingual training data and are confirmed to be effective in terms of quality and speaker similarity of the generated speech.
Proceedings ArticleDOI
Defense Against Adversarial Attacks on Spoofing Countermeasures of ASV
TL;DR: This paper is among the first to use defense methods to improve the robustness of ASV spoofing countermeasure models under adversarial attacks, and the experimental results show that these two defense methods positively help spoofing Countermeasures models counter adversarial examples.