Discriminative training of feature space using maximum mutual information (fMMI) objective function has been shown to yield remarkable accuracy improvements. For noisy environments, fMMI can be regarded as an effective noise compensation algorithm and can play a significant role for noise robustness. Feature space speaker adaptation techniques such as feature space maximum likelihood linear reg...

We propose an improved Tandem system for tonal language speech recognition. Three different types of features, cepstral, spectro-temporal and pitch features, are integrated for modeling tone and phoneme variation simultaneously. Tonal phonemes (or tonemes) are used for MLP posterior estimation, and tonal acoustic units for HMM recognition. In our experiments conducted on Mandarin broadcast news...

We propose to incorporate features derived using spectrotemporal receptive fields (STRFs) of neurons in the auditory cortex for phoneme recognition. Each of these STRFs is tuned to different auditory frequencies, scales and modulation rates. We select different sets of STRFs which are specific for phonemes in different broad phonetic classes (BPC) of sounds. These STRFs are then used as spectro...

We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. The identified Volterra kernels reveal the spectro-temporal patterns that are learned by the trained system for each phoneme. To demonstrate the applicability of Volterra series, we analyze a multilayered perceptron trai...

Pitch plays a fundamental role in audition, from speech and music perception to auditory scene analysis. Congenital amusia is a neurogenetic disorder that appears to affect primarily pitch and melody perception. Pitch is normally conveyed by the spectro-temporal fine structure of low harmonics, but some pitch information is available in the temporal envelope produced by the interactions of high...

We show how the axiomatic structure of scale-space theory can be applied to the auditory domain and be used for deriving idealized models of auditory receptive fields via scale-space principles. For defining a time-frequency transformation of a purely temporal signal, it is shown that the scale-space framework allows for a new way of deriving the Gabor and Gammatone filters as well as a novel f...

Modeling expressive synthesis requires to deal with a wide range of sound’s behavior that include spectral dynamics which are idiomatic to the instrument or characteristic of the playing technique. In the paper we analyze short time evolution of power-spectral envelopes, adaptively changing the analysis parameters so as to variably include filter envelopes, and the pitched excitation parts. Typ...

The spectro-temporal receptive field (STRF) is a model representation of the excitatory and inhibitory integration area of auditory neurons. Recently it has been used to study spectral and temporal aspects of monaural integration in auditory centers. Here we report the properties of monaural STRFs and the relationship between ipsi- and contralateral inputs to neurons of the central nucleus of c...

Investigations of the functional organization of human auditory cortex typically examine responses to different sound categories. An alternative approach is to characterize sounds with respect to their amount of variation in the time and frequency domains (i.e., spectral and temporal complexity). Although the vast majority of published studies examine contrasts between discrete sound categories...