Speech enhancement based on physiological and psychoacoustical models of modulation perception and binaural interaction.

By B. Kollmeier, R. Koch. 1994

How researchers see this paper

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

Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, neutral): “These features include amplitude modulation spectrogram (AMS) [23], relative spectral transform and perceptual linear prediction (RASTA-PLP) [14], [15], mel-frequency cepstral coefficients (MFCC), as well as their deltas.”
Robust speech recognition using the modulation spectrogram (1998, methodology): “…speech representation and its use as 1 It should be noted that, while the representation described here and the speech representation described in Kollmeier and Koch (1994), share the name ``modulation spectrogram'', they are quite distinct in the details of their signal processing and overall…”
Improving Robustness of Deep Neural Network Acoustic Models via Speech Separation and Joint Adaptive Training (2015, background): “The components of the system are described in detail below.”
Speech segregation based on sound localization (2001, methodology): “…differs from bli nd source separation using independent component analysis (Hyväarinen et al., 2001) or spatial filt ering using sensor arrays (Krim and Viberg, 1996); such techniques have strong requirements on the number of sensors that increases as the number of sources increases in an…”
Joint noise adaptive training for robust automatic speech recognition (2014, unknown): “15-dimensional AMS features are extracted separately for each of the 26 frequency bands in the MS.”