Learning when to translate for streaming speech
How to find proper moments to generate partial sentence translation given a streaming
speech input? Existing approaches waiting-and-translating for a fixed duration often break …
speech input? Existing approaches waiting-and-translating for a fixed duration often break …
Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens
While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-
tuned for automatic speech recognition (ASR), downstream performance can still be …
tuned for automatic speech recognition (ASR), downstream performance can still be …
Learning from failure: Data capture in an australian aboriginal community
Most low resource language technology development is premised on the need to collect
data for training statistical models. When we follow the typical process of recording and …
data for training statistical models. When we follow the typical process of recording and …
Local word discovery for interactive transcription
Human expertise and the participation of speech communities are essential factors in the
success of technologies for low-resource languages. Accordingly, we propose a new …
success of technologies for low-resource languages. Accordingly, we propose a new …
Plug-and-Play Multilingual Few-shot Spoken Words Recognition
A Saeed, V Tsouvalas - arXiv preprint arXiv:2305.03058, 2023 - arxiv.org
As technology advances and digital devices become prevalent, seamless human-machine
communication is increasingly gaining significance. The growing adoption of mobile …
communication is increasingly gaining significance. The growing adoption of mobile …
[PDF][PDF] 3.3 ACL 2022: deployment of the sparse transcription simulation
É Le Ferrand, S Bird, LBL From - Leveraging Speech Recognition for …, 2023 - hal.science
Most low resource language technology development is premised on the need to collect
data for training statistical models. When we follow the typical process of recording and …
data for training statistical models. When we follow the typical process of recording and …