End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.
Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the need for force alignment of phonemes. We introduce an automatic segmentation criterion for training from sequence annotation without alignment that is on par with CTC while being simpler. We show competitive results in word error rate on the Librispeech corpus with MFCC features, and promising results from raw waveform.
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
End-to-End ASR for Code-switched Hindi-English Speech
End-to-end ASR for code-switched Hindi-English with <50 hours of data shows gains from multi-task learning and corpus balancing but underperforms cascaded baselines.