SPEECH SYNTHESIS AND RECOGNITION FOR A LOW-RESOURCE LANGUAGE Connecting TTS and ASR for mutual benefit

Makashova, Liliia
University of Gothenburg / Department of Philosophy,Lingustics and Theory of Scienceeng
Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteoriswe
2021-09-23T06:37:00Z
2021-09-23T06:37:00Z
2021-09-23
Speech synthesis (text-to-speech, TTS) and speech recognition (automatic speech recognition, ASR) are the NLP technologies that are the least available for low-resource and indigenous languages. Lack of computational and data resources is the major obstacle when it comes to the development of linguistic tools for these languages. We present a framework that does not require enormous GPU and target data resources, as well as guarantees reasonably good results in performance for the end-product. In this work we perform dual connection between TTS and ASR models and make them learn from each other in a low-resource setup. This project, being the first open-source implementation of such a bidirectional algorithm, leverages the power of open-source projects for the benefit of indigenous languages. We release the first ever functioning ASR tool for the North Sámi language along with a competitive TTS technology, which fulfills the demand of the North Sámi community and globally contributes to the further development of AI tools for low-resource languages.sv
http://hdl.handle.net/2077/69692
engsv
HumanitiesTheology
Speech synthesissv
automatic speech recognitionsv
low-resource languagesv
machine learningsv
transfer learningsv
SPEECH SYNTHESIS AND RECOGNITION FOR A LOW-RESOURCE LANGUAGE Connecting TTS and ASR for mutual benefitsv
Text
Student essay
H2

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
gupea_2077_69692_1.pdf
Size:
1.35 MB
Format:
Adobe Portable Document Format
Description:
master thesis

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
4.68 KB
Format:
Item-specific license agreed upon to submission
Description: