Research output per year
Research output per year
Personal profile
Academic background
Ph.D., The Chinese University of Hong Kong, Hong Kong, S.A.R of China (2015-2020)
B.Eng., Tsinghua University, Beijing, China (2011-2015)
Research interests
Automatic speech recognition, acoustic modeling for low-resource languages, unsupervised acoustic modeling, cross-lingual, and multilingual speech recognition
Research profile
Siyuan Feng received the Ph.D. degree from the Chinese University of Hong Kong, Hong Kong in 2020, and B.Eng. degree from Tsinghua University, Beijing, China, in 2015. He is currently working as a Postdoctoral Researcher in Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands. He has authored and coauthored over ten papers in journal and international conferences, such as IEEE/ACM Transactions on Audio, Speech and Language Processing, International Speech Communication Association and the International Conference on Acoustics, Speech, and Signal Processing. His current research interest includes unsupervised acoustic modeling for low-resource languages, cross-lingual, and multilingual speech recognition
Fingerprint
Dive into the research topics where S. Feng is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Network
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
How phonotactics affect multilingual and zero-shot asr performance
Feng, S., Żelasko, P., Moro-Velázquez, L., Abavisani, A., Hasegawa-Johnson, M., Scharenborg, O. & Dehak, N., 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE , p. 7238-7242 5 p. 9414478Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
Open AccessFile2 Citations (Scopus)18 Downloads (Pure) -
Show and speak: Directly synthesize spoken description of images
Wang, X., Feng, S., Zhu, J., Hasegawa-Johnson, M. & Scharenborg, O., 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE , p. 4190-4194 5 p. 9414021. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
Open AccessFile6 Downloads (Pure) -
The effectiveness of unsupervised subword modeling with autoregressive and cross-lingual phone-aware networks
Feng, S. & Scharenborg, O., 2021, In: IEEE Open Journal of Signal Processing. 2, p. 230 - 247 18 p., 9420327.Research output: Contribution to journal › Article › Scientific › peer-review
Open AccessFile10 Downloads (Pure) -
Unsupervised acoustic unit discovery by leveraging a language-independent subword discriminative feature representation
Feng, S., Zelasko, P., Moro-Velázquez, L. & Scharenborg, O., 2021, 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021. International Speech Communication Association, p. 1534-1538 5 p. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; vol. 2).Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
Open AccessFile1 Downloads (Pure) -
Unsupervised Subword Modeling Using Autoregressive Pretraining and Cross-Lingual Phone-Aware Modeling
Feng, S. & Scharenborg, O., 2020, Proceedings of Interspeech 2020. ISCA, p. 2732 - 2736 5 p. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
Open AccessFile2 Citations (Scopus)8 Downloads (Pure)