34 citations · 116 across the 19 of their papers we have counts for
19 papers
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Junyi Ao, Yuancheng Wang, Xiaohai Tian +6
Speech encompasses a wealth of information, including but not limited to content, paralinguistic, and environmental information. This comprehensive nature of speech significantly i…
CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing
Xianghu Yue, Xiaohai Tian, Lu Lu +3
There has been a long-standing quest for a unified audio-visual-text model to enable various multimodal understanding tasks, which mimics the listening, seeing and reading process…
Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring
Kaiqi Fu, Shaojun Gao, Shuju Shi +3
Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into th…
Leveraging phone-level linguistic-acoustic similarity for utterance-level pronunciation scoring
Wei Liu, Kaiqi Fu, Xiaohai Tian +4
Recent studies on pronunciation scoring have explored the effect of introducing phone embeddings as reference pronunciation, but mostly in an implicit manner, i.e., addition or con…
An ASR-free Fluency Scoring Approach with Self-Supervised Learning
Wei Liu, Kaiqi Fu, Xiaohai Tian +4
A typical fluency scoring system generally relies on an automatic speech recognition (ASR) system to obtain time stamps in input speech for either the subsequent calculation of flu…
TTS-Guided Training for Accent Conversion Without Parallel Data
Yi Zhou, Zhizheng Wu, Mingyang Zhang +2
Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approac…
Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information
Kaiqi Fu, Shaojun Gao, Kai Wang +3
Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data…
The Multi-speaker Multi-style Voice Cloning Challenge 2021
Qicong Xie, Xiaohai Tian, Guanghou Liu +9
The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning t…
NHSS: A Speech and Singing Parallel Database
Bidisha Sharma, Xiaoxue Gao, Karthika Vijayan +2
We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory at the National University of Singapore…
Optimizing voice conversion network with cycle consistency loss of speaker identity
Hongqiang Du, Xiaohai Tian, Lei Xie +1
We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame-level spectral loss, but…
Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions
Rohan Kumar Das, Tomi Kinnunen, Wen-Chin Huang +5
The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary eval…
Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion
Yi Zhao, Wen-Chin Huang, Xiaohai Tian +5
The voice conversion challenge is a bi-annual scientific event held to compare and understand different voice conversion (VC) systems built on a common dataset. In 2020, we organiz…
The Attacker's Perspective on Automatic Speaker Verification: An Overview
Rohan Kumar Das, Xiaohai Tian, Tomi Kinnunen +1
Security of automatic speaker verification (ASV) systems is compromised by various spoofing attacks. While many types of non-proactive attacks (and their defenses) have been studie…
Black-box Attacks on Automatic Speaker Verification using Feedback-controlled Voice Conversion
Xiaohai Tian, Rohan Kumar Das, Haizhou Li
Automatic speaker verification (ASV) systems in practice are greatly vulnerable to spoofing attacks. The latest voice conversion technologies are able to produce perceptually natur…
A Modularized Neural Network with Language-Specific Output Layers for Cross-lingual Voice Conversion
Yi Zhou, Xiaohai Tian, Emre Yılmaz +2
This paper presents a cross-lingual voice conversion framework that adopts a modularized neural network. The modularized neural network has a common input structure that is shared…
A Vocoder-free WaveNet Voice Conversion with Non-Parallel Data
Xiaohai Tian, Eng Siong Chng, Haizhou Li
In a typical voice conversion system, vocoder is commonly used for speech-to-features analysis and features-to-speech synthesis. However, vocoder can be a source of speech quality…
Spoofing detection under noisy conditions: a preliminary investigation and an initial database
Xiaohai Tian, Zhizheng Wu, Xiong Xiao +2
Spoofing detection for automatic speaker verification (ASV), which is to discriminate between live speech and attacks, has received increasing attentions recently. However, all the…
High quality voice conversion using prosodic and high-resolution spectral features
Hy Quy Nguyen, Siu Wa Lee, Xiaohai Tian +2
Voice conversion methods have advanced rapidly over the last decade. Studies have shown that speaker characteristics are captured by spectral feature as well as various prosodic fe…
A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis
Bo Fan, Siu Wa Lee, Xiaohai Tian +2
State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Ma…