3 citations · 10 across the 9 of their papers we have counts for
9 papers
CUHK-EE Systems for the vTAD Challenge at NCMMSC 2025
Aemon Yat Fei Chiu, Jingyu Li, Yusheng Tian +2
This paper presents the Voice Timbre Attribute Detection (vTAD) systems developed by the Digital Signal Processing & Speech Technology Laboratory (DSP&STL) of the Department of Ele…
Personalized Voice Synthesis through Human-in-the-Loop Coordinate Descent
Yusheng Tian, Junbin Liu, Tan Lee
This paper describes a human-in-the-loop approach to personalized voice synthesis in the absence of reference speech data from the target speaker. It is intended to help vocally di…
Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss
Yusheng Tian, Jingyu Li, Tan Lee
This research is about the creation of personalized synthetic voices for head and neck cancer survivors. It is focused particularly on tongue cancer patients whose speech might exh…
Creating Personalized Synthetic Voices from Post-Glossectomy Speech with Guided Diffusion Models
Yusheng Tian, Guangyan Zhang, Tan Lee
This paper is about developing personalized speech synthesis systems with recordings of mildly impaired speech. In particular, we consider consonant and vowel alterations resulted…
Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data
Yusheng Tian, Wei Liu, Tan Lee
Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation. One way to address this problem is to pre-enhan…
Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification
Jingyu Li, Yusheng Tian, Tan Lee
Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism…
Transport-Oriented Feature Aggregation for Speaker Embedding Learning
Yusheng Tian, Jingyu Li, Tan Lee
Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize…
Learnable Frequency Filters for Speech Feature Extraction in Speaker Verification
Jingyu Li, Yusheng Tian, Tan Lee
Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all differe…
Improving End-to-End Speech-to-Intent Classification with Reptile
Yusheng Tian, Philip John Gorinski
End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system i…