MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION

MixSpeech is a data augmentation method for automatic speech recognition, which trains an ASR model by taking a weighted combination of two different speech features as the input, and recognizing both text sequences.

Data and Resources

Cite this as

Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu (2024). Dataset: MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION. https://doi.org/10.57702/ttn4s8ar

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Linghui Meng
More Authors
Jin Xu
Xu Tan
Jindong Wang
Tao Qin
Bo Xu