The project covers automatic speech recognition with neural network training using low-dimensional matrix factorization. We are describing time delay neural networks with factorization (TDNN-F) and without it (TDNN) in Pytorch language. We are comparing the implementation between Pytorch and Kaldi toolkit, where we achieve similar results during experiments with various network architectures. The last chapter describes the impact of a low-dimensional matrix factorization on End-to-End speech recognition systems and also a modification of the system with TDNN(-F) networks. Using specific network settings, we were able to achieve better results with systems using factorization. Additionally, we reduced the complexity of training by decreasing network parameters with the use of TDNN(-F) networks.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:417297 |
| Date | January 2020 |
| Creators | Gajdár, Matúš |
| Contributors | Grézl, František, Karafiát, Martin |
| Publisher | Vysoké učení technické v Brně. Fakulta informačních technologií |
| Source Sets | Czech ETDs |
| Language | Slovak |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.1962 seconds