Semi-supervised GMM and DNN acoustic model training with multi-system combination and confidence re-calibration

63 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.

Deep Learning: Methods and Applications (2014, background): “[176] reported another variant of semi-supervised training technique in which multisystem combination and confidence recalibration is applied to select the training data.”
Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models (2016, methodology): “A method combining multi-system combination with confidence score calibration was proposed in [10].”
Semi-supervised ASR by End-to-end Self-training (2020, background): “It has been shown to be very effective with traditional ASR pipelines [1, 2, 3, 4].”
A big data approach to acoustic model training corpus selection (2014, methodology): “Rather than relying on small supervised training sets, one can instead exploit the large amount of audio data that is processed by systems like Voice Search, together with semi-supervised techniques to construct large training sets with automatically derived transcripts [4, 5, 6, 7, 8].”
Semi-supervised training of Deep Neural Networks (2013, methodology): “Very practical are the self-training methods [1] [2][3], in which the transcribed data are used to build a seed model.”