| Paper ID | MLSP-34.6 |
| Paper Title |
A HIERARCHICAL SUBSPACE MODEL FOR LANGUAGE-ATTUNED ACOUSTIC UNIT DISCOVERY |
| Authors |
Bolaji Yusuf, Bogazici University, Turkey; Lucas Ondel, Lukáš Burget, Jan "Honza" Cernocky, Brno University of Technology, Czechia; Murat Saraclar, Bogazici University, Turkey |
| Session | MLSP-34: Subspace Learning and Applications |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation Time: | Thursday, 10 June, 15:30 - 16:15 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-SBML] Subspace and manifold learning |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy. |
