Massey University

Resources

Zhihan Wang, Feng Hou and Ruili Wang (2026) Synthesized Data Selection via Score Distribution Matching for Te Reo Māori Automatic Speech Recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026 (accepted)

Read Abstract Read Online

C. Lei, F. Hou, H. Jahnke and R. Wang (2025) Parameter-Efficient Personalized Speech Synthesis via EMD-based Speaker Modeling, 2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Eindhoven, Netherlands, 2025, pp. 551-556

Read Abstract Read Online

S. Singh, F. Hou, R. Wang (2023) A Novel Self-training Approach for Low-resource Speech Recognition, In Proc. Interspeech 2023, 1588-1592.

Read Abstract Read Online

Z. Wang, F. Hou, R. Wang (2023) CLRL-Tuning: A Novel Continual Learning Approach for Automatic Speech Recognition. In Proc. Interspeech 2023, 1279-1283.

Read Abstract Read Online

S. Singh, R. Wang, F. Hou* (2022) Improved Meta Learning for Low Resource Speech Recognition. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4798-4802). IEEE, Singapore.

Read Abstract Read Online

Z. Wang, F. Hou, Y. Qiu, Z. Ma, S. Singh, R. Wang (2022) CyclicAugment: Speech Data Random Augmentation With Cosine Annealing Scheduler For Speech Recognition. In Proc. Interspeech 2022, 3859-3863.

Read Abstract Read Online

Ma, Z., Qiu, Y., Hou, F., Wang, R., Chu, JTW., & Bullen, C. (2022). Determining the best Acoustic Features for Smoker Identification. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2022-May (pp. 8177 - 8181).

Read Abstract Read Online

F. Hou, R. Wang, S. Ng, F. Zhu, M. Witbrock, S. Cahan, L. Chen and X. Jia (2023) Anisotropic span embeddings and the negative impact of higher-order inference for coreference resolution, Natural Language Engineering [Accepted].

Read Abstract Read Online

F. Hou, R. Wang, S. Ng, M. Witbrock, F. Zhu and X. Jia (2022) Exploiting Anonymous Entity Mentions for Named Entity Linking, Knowledge and Information Systems, 65, 1221–1242 (2023)

Read Abstract Read Online

R. Wang, F. Hou*, S. Cahan, L. Chen, X. Jia and W. Ji (2022) Fine-grained Entity Typing with a Type Taxonomy: a Systematic Review, IEEE Transactions on Knowledge and Data Engineering, https://doi.org/10.1109/TKDE.2022.3148980.

Read Abstract Read Online

Y. Qiu, R. Wang, F. Hou*, S. Singh, Z. Ma and X. Jia (2022) Adversarial Multi-task Learning with Inverse Mapping for Speech Enhancement, Applied Soft Computing, 120, p.108568, 2022.

Read Abstract Read Online

F. Hou, R. Wang (corresponding author), Y. Zhou (2021) Transfer learning for fine-grained entity typing, Knowledge and Information Systems, Issue 4.

Read Abstract Read Online

Y. Qiu, R. Wang*, S. Singh, Z. Ma and F. Hou (2021) Self-Supervised Learning Based Phone-Fortified Speech Enhancement. In Proceedings of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH), Hybrid Event, Brno, Czechia, 30 August-3 September 2021.

Read Abstract Read Online

Authors Discription Type Action

Yuan Gao, Feng Hou*, Huia Jahnke, Ruili Wang

Data Augmentation with Diversified Rephrasing for Low-Resource Neural Machine Translation

PDF Download

Feng Hou and Ruili Wang

Approaches for Low-resource Neural Machine Translation

PDF Download

Name Discription Type Version Action

Punjabi Speech

The Punjabi Speech corpus is designed for automatic speech recognition and synthesis purposes.

Speech v2 Download

Google-Synth

The Google-synth dataset comprises a synthetic Punjabi dataset that has been generated using Google's Cloud Text-to-Speech service.

Speech v1 Download

CMU-synth

The CMU-synth dataset is a synthetic Punjabi dataset generated using CMU's Clustergen text-to-speech model.

Speech v1 Download