Noise robust speech recognition using delta-cepstrum normalization and channel selection

Robust speech recognition in additive an

Robust speech recognition in additive and convolutional noise using parallel model combination

✍ M.F.J. Gales; S.J. Young 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 166 KB

The method of Parallel Model Combination (PMC) has been shown to be a powerful technique for compensating a speech recognizer for the effects of additive noise. In this paper, the PMC scheme is extended to include the effects of convolutional noise. This is done by introducing a modified "mismatch"