speech-11
Speech Recognition
3260 papers • 126 benchmarks • 313 datasets
Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise. ( Image credit: SpecAugment )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in speech-recognition-11
Trend
Dataset
Best Model
Actions
LibriSpeech test-clean
LibriSpeech test-clean
LibriSpeech test-other
LibriSpeech test-other
TIMIT
Libraries
iUse these libraries to find speech-recognition-11 models and implementations
13 papers 29
Datasets
Subtasks
Most implemented papers
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Quoc V. Le, E. D. Cubuk, Barret Zoph, Yu Zhang, William Chan, Daniel S. Park, Chung-Cheng Chiu•Thu Apr 18 2019
This work presents SpecAugment, a simple data augmentation method for speech recognition that is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients) and achieves state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work.
3885
