Improved noise robustness of word HMMs based on weighted variance expansion for noisy speech recognition

2005 ◽  
Vol 36 (13) ◽  
pp. 57-68
Author(s):  
Sukeyasu Kanno ◽  
Tetsuo Funada
Keyword(s):  
Speech Recognition ◽  
Noise Robustness ◽  
Noisy Speech ◽  
Noisy Speech Recognition

scholarly journals End-to-End Noisy Speech Recognition Using Fourier and Hilbert Spectrum Features

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1157 ◽  
Author(s):  
Daria Vazhenina ◽  
Konstantin Markov
Keyword(s):  
Speech Recognition ◽  
Speech Processing ◽  
Data Augmentation ◽  
Recognition System ◽  
Noise Robustness ◽  
Hilbert Spectrum ◽  
Noisy Speech ◽  
Hilbert Huang Transform ◽  
Noisy Speech Recognition ◽  
Non Stationary Signal

Despite the progress of deep neural networks over the last decade, the state-of-the-art speech recognizers in noisy environment conditions are still far from reaching satisfactory performance. Methods to improve noise robustness usually include adding components to the recognition system that often need optimization. For this reason, data augmentation of the input features derived from the Short-Time Fourier Transform (STFT) has become a popular approach. However, for many speech processing tasks, there is an evidence that the combination of STFT-based and Hilbert–Huang transform (HHT)-based features improves the overall performance. The Hilbert spectrum can be obtained using adaptive mode decomposition (AMD) techniques, which are noise-robust and suitable for non-linear and non-stationary signal analysis. In this study, we developed a DeepSpeech2-based recognition system by adding a combination of STFT and HHT spectrum-based features. We propose several ways to combine those features at different levels of the neural network. All evaluations were performed using the WSJ and CHiME-4 databases. Experimental results show that combining STFT and HHT spectra leads to a 5–7% relative improvement in noisy speech recognition.

scholarly journals Cepstral Normalization Combined with CSFN for Noisy Speech Recognition

2011 ◽  
Vol 14 (10) ◽  
pp. 1221-1228
Author(s):  
Sook-Nam Choi ◽  
Guang-Hu Shen ◽  
Hyun-Yeol Chung
Keyword(s):  
Speech Recognition ◽  
Noisy Speech ◽  
Noisy Speech Recognition

Complex spectrum circle centroid for microphone-array-based noisy speech recognition

2004 ◽  
Author(s):  
Shigeki Sagayama ◽  
Okajima Takashi ◽  
Kamamoto Yutaka ◽  
Nishimoto Takuya
Keyword(s):  
Speech Recognition ◽  
Microphone Array ◽  
Complex Spectrum ◽  
Noisy Speech ◽  
Noisy Speech Recognition
Sign in / Sign up

Export Citation Format

Share Document