Siyuan Feng

Siyuan Feng

Auto-generated profile, based on publicly available information

Siyuan Feng

Multimedia Computing Group, Delft University of Technology, 2860 Delft, South Holland, Netherlands

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
2 September 2018
Verified
Conference Paper
Closed access
YQYing Qin
Ying Qin
TLTan Lee
Tan Lee
SFSiyuan Feng
Siyuan Feng
AKAnthony Pak Hin Kong
Anthony Pak Hin Kong

9 February 2022 in Computer Speech & Language
Verified
Journal Article
Closed access
PŻPiotr Żelasko
Piotr Żelasko
SFSiyuan Feng
Siyuan Feng
LMLaureano Moro-Velazquez
Laureano Moro-Velazquez
AAAli Abavisani
Ali Abavisani
SBSaurabhchand Bhati
Saurabhchand Bhati
NDNajim Dehak
Najim Dehak

15 September 2019
Verified
Conference Paper
Closed access
SFSiyuan Feng
Siyuan Feng
TLTan Lee
Tan Lee
ZPZhiyuan Peng
Zhiyuan Peng

9 May 2022 in Speech Communication
Verified
Journal Article
Open access
BHBence Mark Halpern
Bence Mark Halpern
SFSiyuan Feng
Siyuan Feng
RSRob van Son
Rob van Son
Michiel Van den BrekelMichiel Van den Brekel
Michiel Van den Brekel
OSOdette Scharenborg
Odette Scharenborg

28 August 2019 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
SFSiyuan Feng
Siyuan Feng
TLTan Lee
Tan Lee
This research addressed the problem of acoustic modeling of low-resource languages for which transcribed training data are absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish subword-level speech units. The proposed feature representations comprise various types of multilingual bottleneck features (BNFs) that are obtained via multi-task learning of deep neural networks (MTL-DNN). One of the key problems is how to acquire high-quality frame labels for untranscribed training data to facilitate supervised DNN training. It is shown that learning of robust BNF representations can be achieved by effectively leveraging transcribed speech data and well-trained automatic speech recognition (ASR) systems from one or more out-of-domain (resource-rich) languages. Out-of-domain ASR systems can be applied to perform speaker adaptation with untranscribed training data of the target language, and to decode the training speech into frame-level labels for DNN training. It is also found that better frame labels can be generated by considering temporal dependency in speech when performing frame clustering. The proposed methods of feature learning are evaluated on the standard task of unsupervised subword modeling in Track 1 of the ZeroSpeech 2017 Challenge. The best performance achieved by our system is 9.7% in terms of across-speaker triphone minimal-pair ABX error rate, which is comparable to the best systems reported recently. Lastly, our investigation reveals that the closeness between target languages and out-of-domain languages and the amount of available training data for individual target languages could have significant impact on the goodness of learned features.