Pu Wang

Pu Wang

Auto-generated profile, based on publicly available information

Pu Wang

Department of Electrical Engineering-ESAT, KU Leuven, Leuven, Belgium

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in Computers in Industry
Verified
Journal Article
Closed access
SSSiyu Shao
Siyu Shao
PWPu Wang
Pu Wang
RYRuqiang Yan
Ruqiang Yan

24 July 2019 in IEEE Access
Verified
Journal Article
Open access
PWPu Wang
Pu Wang
BHBorui Hou
Borui Hou
SSSiyu Shao
Siyu Shao
RYRuqiang Yan
Ruqiang Yan

7 April 2023 in EURASIP Journal on Audio, Speech, and Music Processing
Verified
Journal Article
Open access
PDF file
PWPu Wang
Pu Wang
HHHugo Van Hamme
Hugo Van Hamme
With the rise of deep learning, spoken language understanding (SLU) for command-and-control applications such as a voice-controlled virtual assistant can offer reliable hands-free operation to physically disabled individuals. However, due to data scarcity, it is still a challenge to process dysarthric speech. Pre-training (part of) the SLU model withsupervisedautomatic speech recognition (ASR) targets or withself-supervisedlearning (SSL) may help to overcome a lack of data, but no research has shown which pre-training strategy performs better for SLU on dysarthric speech and to which extent the SLU task benefits from knowledge transfer from pre-training with dysarthric acoustic tasks. This work aims to compare different mono- or cross-lingual pre-training (supervisedandunsupervised) methodologies and quantitatively investigates the benefits of pre-training for SLU tasks on Dutch dysarthric speech. The designed SLU systems consist of a pre-trained speech representations encoder and a SLU decoder to map encoded features to intents. Four types of pre-trained encoders, a mono-lingual time-delay neural network (TDNN) acoustic model, a mono-lingual transformer acoustic model, a cross-lingual transformer acoustic model (Whisper), and a cross-lingual SSL Wav2Vec2.0 model (XLSR-53), are evaluated complemented with three types of SLU decoders: non-negative matrix factorization (NMF), capsule networks, and long short-term memory (LSTM) networks. The acoustic analysis of the four pre-trained encoders are tested on Dutch dysarthric home-automation data with word error rate (WER) results to investigate the correlations of the dysarthric acoustic task (ASR) and the semantic task (SLU). By introducing the intelligibility score (IS) as a metric of the impairment severity, this paper further quantitatively analyzes dysarthria-severity-dependent models for SLU tasks.

20 March 2019 in IEEE Access
Verified
Journal Article
Open access
PWPu Wang
Pu Wang
HWHui Wang
Hui Wang
RYRuqiang Yan
Ruqiang Yan

1 January 2025 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
PWPu Wang
Pu Wang
HHHugo Van hamme
Hugo Van hamme

26 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
PWPu Wang
Pu Wang
HHHugo Van hamme
Hugo Van hamme
End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improving ASR performance.