Speaker adaptation of context dependent deep neural networks based on MAP-adaptation and GMM-derived feature processing

By Natalia A. Tomashenko, Yuri Y. Khokhlov. 2014

27 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Speech & Audio, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Sahar Ghannay
2. François Hernandez
3. Natalia A. Tomashenko
4. Yannick Estève
5. Gabriel Synnaeve
6. Ronan Collobert
7. Qiantong Xu
8. Tatiana Likhomanenko

In Representation & Self-Supervised Learning

1. François Hernandez
2. Yannick Estève
3. Sahar Ghannay
4. Natalia A. Tomashenko

In Speech & Audio

1. François Hernandez
2. Sahar Ghannay
3. Natalia A. Tomashenko
4. Yannick Estève
5. Gabriel Synnaeve
6. Ronan Collobert
7. Qiantong Xu
8. Tatiana Likhomanenko

In Signal Processing

1. Yannick Estève
2. François Hernandez
3. Sahar Ghannay
4. Natalia A. Tomashenko
5. Gabriel Synnaeve
6. Ronan Collobert
7. Qiantong Xu
8. Tatiana Likhomanenko

Citations in the corpus

• TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation (2018, methodology): “eport experimental results obtained on the speaker adaptation distribution by exploiting TDNN-Long Short-Term Memory (TDNN-LSTM) acoustic models [7] and Gaussian Mixture Model-derived (GMMD) features [14]. The last section is dedicated to discussion and conclusion. 2 TED-LIUM 3 Corpus description 2.”