Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition
スポンサーリンク
概要
- 論文の詳細を見る
This paper presents a new feature extraction method for robust speech recognition based on the autocorrelation mel frequency cepstral coefficients (AMFCCs) and a variable window. While the AMFCC feature extraction method uses the fixed double-dynamic-range (DDR) Hamming window for higher-lag autocorrelation coefficients, which are least affected by noise, the proposed method applies a variable window, depending on the frame energy and periodicity. The performance of the proposed method is verified using an Aurora-2 task, and the results confirm a significantly improved performance under noisy conditions.
論文 | ランダム
- An Application of the Mercier Criterion to a Tokamak Plasma with an Elliptical Cross Section
- 大学の海外体験学習プログラムにおけるコーディネーターの役割--桜美林大学での実践から
- EFFECTS OF NO_2 AND O_3 EXPOSURE ALONE OR IN COMBINATION ON KIDNEY BEAN PLANTS : AMINO ACID CONTENT AND COMPOSITION
- DETERMINATION OF ^C IN PLANT MATERIALS BY INFRARED ABSORPTION SPECTROMETRY USING A SIMPLE CALIBRATION METHOD
- Developing the test of English ability (TEA)