UHH>Informatik>NatS>Addis2023 Web>CourseStructure>ScheDule>QSM16 (12 Mar 2023, WolfgangMenzel) Print version
Questions for self-monitoring
- What are typical characteristics of ASR tasks?
- How can the encoder-decoder architecture be applied to speech recognition?
- Why an external language model is used? Can't it be trained as part of the encoder decoder?
- How does Connectionist Temporal Classification (CTC) work?
- How a CTC model is trained?
- What are the advantages and drawbacks of CTC?
- How is the quality of ASR measured? How can the significance of the results be estimated?
 |
|
Copyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors. Ideas, requests, problems regarding Foswiki? Send feedback