Tandem Connectionist Feature Extraction for Conversational Speech Recognition

23 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Speech recognition with deep recurrent neural networks (2013, background): “Neural networks have a long history in speech recognition, usually in combination with hidden Markov models [1, 2].”
Hybrid speech recognition with Deep Bidirectional LSTM (2013, methodology): “The standard solution to the problem of training neural networks for speech recognition is to merge them with HMMs in the so-called hybrid [4] or tandem [5] models.”
End-to-End attention based text-dependent speaker verification (2016, background): “The bottleneck features can also be incorporated together with the input MFCC features as Tandem features [27].”
Convolutional Neural Networks for Speech Recognition (2014, background): “…[6], [7], [8], [9], initially on the TIMIT phone recognition task with mono-phone HMMs for MFCC features [10], [11], [12], and shortly thereafter on several large vocabularyASR taskswithtriphoneHMM models [6], [7], [13], [14], [15], [16]; see an overview of this series of studies in [17].”