International Journal of Computer Vision · 2018 · 202 citations · 42 references
ComputingComputer ScienceComputational LinguisticsComputer VisionMachine LearningDeep LearningGesture AnalysisGesture RecognitionPattern RecognitionSpeech RecognitionContinuous Sign Language RecognitionError Rate AnalysisPretrainingPretraining ObjectivesSequence Data IntegrationSequence Modeling For GesturesSign Language RecognitionWord Error Rate
This manuscript introduces the end-to-end embedding of a CNN into a HMM, while interpreting the outputs of the CNN in a Bayesian framework. The hybrid CNN-HMM combines the strong discriminative abilities of CNNs with the sequence modelling capabilities of HMMs. Most current approaches in the field of gesture and sign language recognition disregard the necessity of dealing with sequence data both for training and evaluation. With our presented end-to-end embedding we are able to improve over the state-of-the-art on three challenging benchmark continuous sign language recognition tasks by between 15 and 38% relative reduction in word error rate and up to 20% absolute. We analyse the effect of the CNN structure, network pretraining and number of hidden states. We compare the hybrid modelling to a tandem approach and evaluate the gain of model combination.
42
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations