Linear prediction of the one-sided autocorrelation sequence for noisy speech recognition

Javier Hernando, Climent Nadeu · IEEE Transactions on Speech and Audio Processing · 1997

The article presents a robust representation of speech based on AR modeling of the causal part of the autocorrelation sequence. In noisy speech recognition, this new representation achieves better results than several other related techniques.

Read the paper · More papers on PaperTik