The application of Missing Data Theory (MDT) has shown to improve the robustness of automatic speech recognition (ASR) systems. A crucial part in a MDT-based recognizer is the computation of the reliability masks from noisy data. To estimate accurate masks in environments with unknown, non-stationary noise statistics only weak assumptions can be made about the noise and we need to rely on a str...

This study introduces a corpus of 260 naturalistic human nonlinguistic vocalizations representing nine emotions: amusement, anger, disgust, effort, fear, joy, pain, pleasure, and sadness. The recognition accuracy in a rating task varied greatly per emotion, from <40% for joy and pain, to >70% for amusement, pleasure, fear, and sadness. In contrast, the raters' linguistic-cultural group had no e...

In this paper we propose a running demonstration of coupling between an intermediate processing step (named CASA), based on the harmonicity cue, and partial recognition, implemented with a HMM/ANN multistream technique 2]. The model is able to recognise words corrupted with narrow band noise, either stationary or having variable center frequency. The principle is to identify frame by frame the ...

A noise synthesis method with no external connotation is proposed. By creating atoms with random width, onset-time and frequency, most external connotations are avoided. The further addition of a frequency distribution corresponding to the perceptual Bark frequency, and a spectrum corresponding to the equalloudness contour for a given phon level further removes the synthesis from the common sig...

In everyday listening, both background noise and reverberation degrade the speech signal. While monaural speech separation based on periodicity has achieved considerable progress in handling additive noise, little research has been devoted to reverberant scenarios. Reverberation smears the harmonic structure of speech signals, and our evaluations using a pitch-based separation algorithm show th...

We define a new theory of discrete Riemann surfaces and present its basic results. The key idea is to consider not only a cellular decomposition of a surface, but the union with its dual. Discrete holomorphy is defined by a straightforward discretisation of the Cauchy-Riemann equation. A lot of classical results in Riemann theory have a discrete counterpart, Hodge star, harmonicity, Hodge theor...

We describe the first stage of a two-stage semialgorithmic approach to music performance rendering. In the first stage, we estimate the perceptual salience of immanent accents (phrasing, metrical, melodic, harmonic) in the musical score. In the second, we manipulate timing, dynamics and other performance parameters in the vicinity of immanent accents (e. g., getting slower and/or louder near an...

This paper proposes a robust feature extraction for voice activity detection (VAD) in noisy environments where nonstationary noises exist. The accuracy of the VAD is drastically reduced because the fluctuation of features at the noise intervals causes false alarm rate to being increased. In this paper, in order to improve the VAD accuracy, harmonic-weighted energy is proposed. This feature extr...

Many topics in integrable surface geometry may be unified by application of the highly developed theory of harmonic maps of surfaces into (pseudo-)Riemannian symmetric spaces. On the one hand, such harmonic maps comprise an integrable system with spectral deformations, algebro-geometric solutions and dressing actions of loop groups generated by Bäcklund transforms [5], [6], [14], [21], [24]. On...

The lowest fingerings of the saxophone can lead to several different regimes, depending on musician’s control and characteristics instrument. This is explored in this paper through a physical model saxophone. harmonic balance method shows that for many combinations musician parameters, regimes are stable. Time-domain synthesis used show how be selected initial conditions evolution (rising time)...