Login
- Titel:
CTC-Segmentation of Large Corpora for German End-to-End Speech Recognition
- Dokumenttyp:
- Konferenzbeitrag
- Autor(en):
- Kürzinger, Ludwig; Winkelbauer, Dominik; Li, Lujun; Watzel, Tobias; Rigoll, Gerhard
- Abstract:
- Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance.
- Herausgeber:
- Karpov, Alexey; Potapova, Rodmonga
- Kongress- / Buchtitel:
- Speech and Computer
- Verlag / Institution:
- Springer International Publishing
- Verlagsort:
- Cham
- Jahr:
- 2020
- Monat:
- Sep
- Seiten:
- 267--278
- Print-ISBN:
- 978-3-030-60276-5
BibTeX
Vorkommen:
- mediaTUM GesamtbestandEinrichtungenSchools TUM School of Computation, Information and TechnologyDepartmentsComputer EngineeringMensch-Maschine-Kommunikation (Prof. Rigoll)AuthorWatzel
- mediaTUM GesamtbestandEinrichtungenSchools TUM School of Computation, Information and TechnologyDepartmentsComputer EngineeringMensch-Maschine-Kommunikation (Prof. Rigoll)AuthorKürzinger
- mediaTUM GesamtbestandEinrichtungenSchools TUM School of Computation, Information and TechnologyDepartmentsComputer EngineeringMensch-Maschine-Kommunikation (Prof. Rigoll)Publication Year2020
- mediaTUM GesamtbestandHochschulbibliographie2020FakultätenElektrotechnik und InformationstechnikMensch-Maschine-Kommunikation (Prof. Rigoll)