While neural text-to-speech (TTS) has achieved human-like natural synthe...
Research on speech-to-speech translation (S2ST) has progressed rapidly i...
Most recent speech recognition models rely on large supervised datasets,...
As audio-visual systems are being deployed for safety-critical tasks suc...
There has been many studies on improving the efficiency of shared learni...
In voice conversion (VC), an approach showing promising results in the l...
Models pre-trained on multiple languages have shown significant promise ...
There is growing interest in ASR systems that can recognize phones in a
...
With recent advancements in language technologies, humansare now interac...
In the problem of learning disentangled representations, one of the prom...
Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-graine...
Despite recent advances in natural language processing and other languag...
We introduce a new resource, AlloVera, which provides mappings from 218
...
Multilingual models can improve language processing, particularly for lo...
Automatic phonemic transcription tools are useful for low-resource langu...
Voice Assistants (VAs) such as Amazon Alexa or Google Assistant rely on
...
While low resource speech recognition has attracted a lot of attention f...
Multilingual acoustic models have been successfully applied to low-resou...
This paper describes the ARIEL-CMU submissions to the Low Resource Human...
Building multilingual and crosslingual models help bring different langu...
The input method is an essential service on every mobile and desktop dev...
Developing a practical speech recognizer for a low resource language is
...