Sources of degradation of speech recognition in the telephone network

By Pedro J. Moreno Mengibar, Richard M. Stern. 1994

Subfields: Speech & Audio

How researchers see this paper

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

In Speech & Audio

1. Jinyu Li
2. Yifan Gong
3. Dong Yu
4. Chin-Hui Lee
5. Xiangang Li
6. Jun Du
7. Ne Luo
8. Wubo Li

Citations in the corpus

• Improving Transformer-based Speech Recognition Using Unsupervised Pre-training (2019, background): “Note downsampling would usually hurt the accuracy of speech recognition system [22, 23] and results for AISHELL-1 is usually reported on the original 16kHz data.”
• An experimental study on joint modeling of mixed-bandwidth data via deep neural networks for robust speech recognition (2016, background): “It can boost the recognition performance of narrowband speech with the additional down-sampled data while sacrificing the performance of wideband speech as the high-frequency information is lost [1] during down-sampling.”
• Improving wideband speech recognition using mixed-bandwidth training data in CD-DNN-HMM (2012, background): “Index Terms— deep neural network, log filter bank, CDDNN-HMM, wideband, narrowband, mixed-bandwidth”