Context dependent phone models for LSTM RNN acoustic modelling

53 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.

A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese (2018, background): “CD-states and CD-phonemes are dominant as their modeling units in such systems [1, 2, 3].”
Fast and accurate recurrent neural network acoustic models for speech recognition (2015, background): “Previously, [22] it was shown that it is possible to build context dependent whole-phone models, and that for LSTM-HMM”
A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition (2016, background): “[3, 4, 10, 11, 12, 13, 14, 15] investigate various bidirectional and unidirectional LSTM topologies with optional projection in some cases combined with convolutional or feed-forward layers for acoustic modeling in ASR.”
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition (2016, methodology): “Since we have more data available, and models that can capture longer temporal context, we show results for single-state CD phone units [25]; this gives a 4% relative improvement over the 3-state triphone models.”
Lower Frame Rate Neural Network Acoustic Models (2016, methodology): “To facilitate CTC training these CTC-LSTM models used one-state, context dependent phones (CD-Phones) [8].”