Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen:
http://dx.doi.org/10.18419/opus-11524
Autor(en): | Serai, Dhiren Devinder |
Titel: | Quantization of automatic speech recognition networks |
Erscheinungsdatum: | 2020 |
Dokumentart: | Abschlussarbeit (Master) |
Seiten: | 60 |
URI: | http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-115417 http://elib.uni-stuttgart.de/handle/11682/11541 http://dx.doi.org/10.18419/opus-11524 |
Zusammenfassung: | Recently, end-to-end neural networks based speech recognition systems have received great interests in the speech community. Although these systems offer a wide range of advantages such as high performance, they often rely on a neural network with a large number of parameters, i.e. large memory footprint and large decoding time. The main goal of this thesis is investigation of quantized neural networks for end-to-end speech recognition systems. Different quantization methods like post training quantization, scalar quantization, iterative product quantization and quantization aware training are investigated in this thesis on ASR model. By doing so, the final system is 3.7 times smaller than the baseline system, faster in decoding with a speedup factor of 1.19 and with almost same level of recognition performance. |
Enthalten in den Sammlungen: | 05 Fakultät Informatik, Elektrotechnik und Informationstechnik |
Dateien zu dieser Ressource:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
Serai_Masterarbeit.pdf | 993,48 kB | Adobe PDF | Öffnen/Anzeigen |
Alle Ressourcen in diesem Repositorium sind urheberrechtlich geschützt.