Home > Search Results: Vainer, Jan
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Efficient neural speech synthesis
 Vainer, Jan ; Dušek, Ondřej (advisor) ; Hajič, Jan (referee)
While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. In this the- sis, we present a neural speech synthesis system capable of high-quality faster- than-real-time spectrogram synthesis, with low requirements on computational resources and fast training time. Our system consists of a teacher and a student network. The teacher model is used to extract alignment between the text to synthesize and the corresponding spectrogram. The student uses the alignments from the teacher model to synthesize mel-scale spectrograms from a phonemic representation of the input text efficiently. Both systems utilize simple convo- lutional layers. We train both systems on the english LJSpeech dataset. The quality of samples synthesized by our model was rated significantly higher than baseline models. Our model can be efficiently trained on a single GPU and can run in real time even on a CPU. 1
Detailed record
Extending Hotelling's location model into Agent-based domain
 Vainer, Jan ; Kukačka, Jiří (advisor) ; Smutná, Šarlota (referee)
This thesis examines behaviour of adaptive agents in Hotelling's location model. We conduct an agent-based simulation in Hotelling's setting with two agents, where the agents use Nash-Q learning mechanism for adaptation. Traditional game-theoretic models often stand on strong assumptions imposed on players such as rationality and perfect information. We explore what alternations or re- finements of results this technique brings in comparison to the original analytical solution of the theoretical Hotelling's location model. We discover that under Nash-Q learning and quadratic consumer cost func- tion, agents with high enough valuation of future profits learn behaviour similar to aggressive market strategy, where both agents make similar products and lead a price war in order to eliminate their opponent from the market. This be- haviour closely resembles the Minimum differentiation principle from the original Hotelling's paper with linear consumer costs. This result is surprising because in our simulation, quadratic consumer cost functions are used, which should result in maximum differentiation of the products. Our results suggest that the Prin- ciple of minimum differentiation could be justified based on repeated interaction of the agents and long-run optimization. Additionally, suitability of...
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English