On speaker adaptation of long short-term memory recurrent neural networks

44 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.

Neural Voice Cloning with a Few Samples (2018, methodology): “The ﬁrst group is speaker adaptation for the whole-model [Yu et al., 2013], a portion of the model [Miao and Metze, 2015, Cui et al., 2017], or merely to a speaker embedding [Abdel-Hamid and Jiang, 2013, Xue et al., 2014].”
EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding (2015, methodology): “[13, 14, 15] as the acoustic models, and the Long Short-Term Memory (LSTM) units [16, 17, 18, 19] as the RNN building blocks.”
On Multi-Domain Training and Adaptation of End-to-End RNN Acoustic Models for Distant Speech Recognition (2017, background): “data, keeping the rest of the network unchanged [22, 23].”
Continual Adaptation for Efficient Machine Communication (2019, background): “However, the interactive communicative setting we consider poses several distinct challenges from traditional speech recognition (Miao and Metze, 2015) or text classification settings (Blitzer et al.”
Recent progresses in deep learning based acoustic models (2017, background): “Although the initial purpose of LSTMP is to reduce runtime cost, it was also reported helpful to error rate reduction [8], [26] which is possibly because parameter reduction helps to generalize better if the LSTM model is too strong.”
Transfer learning for speech and language processing (2015, background): “For example, [105] reported an extensive study on speaker adaptation for LSTMs.”