Speech Recognition On Timit

Percentage error

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표

모델 이름	Percentage error
the-pytorch-kaldi-speech-recognition-toolkit	16.3
long-short-term-memory-and-learning-to-learn	33.2
wav2vec-unsupervised-pre-training-for-speech	14.7
wav2vec-2-0-a-framework-for-self-supervised	8.3
the-pytorch-kaldi-speech-recognition-toolkit	14.5
the-pytorch-kaldi-speech-recognition-toolkit	14.2
quaternion-convolutional-neural-networks-for-1	19.64
the-pytorch-kaldi-speech-recognition-toolkit	16.0
speech-recognition-with-deep-recurrent-neural	17.7
the-pytorch-kaldi-speech-recognition-toolkit	14.9
attention-model-for-articulatory-features	20.4
light-gated-recurrent-units-for-speech	16.7
모델 13	16.5
the-pytorch-kaldi-speech-recognition-toolkit	15.9
the-pytorch-kaldi-speech-recognition-toolkit	16.6
segmental-recurrent-neural-networks-for-end	17.3
the-pytorch-kaldi-speech-recognition-toolkit	16.5
attention-based-models-for-speech-recognition	17.6
모델 19	16.7
vq-wav2vec-self-supervised-learning-of-1	11.6
light-gated-recurrent-units-for-speech	14.9
online-and-linear-time-attention-by-enforcing	20.1