scholarly journals Ultrasonic Doppler Based Silent Speech Interface Using Perceptual Distance

2022 ◽  
Vol 12 (2) ◽  
pp. 827
Author(s):  
Ki-Seung Lee
Keyword(s):  
Speech Signals ◽  
Perceptual Evaluation ◽  
Perceptual Distance ◽  
Speech Interface ◽  
Synthesized Speech ◽  
Actual Speech ◽  
The Difference ◽  
Feasibility Test ◽  
Short Time ◽  
Silent Speech

Moderate performance in terms of intelligibility and naturalness can be obtained using previously established silent speech interface (SSI) methods. Nevertheless, a common problem associated with SSI has involved deficiencies in estimating the spectrum details, which results in synthesized speech signals that are rough, harsh, and unclear. In this study, harmonic enhancement (HE), was used during postprocessing to alleviate this problem by emphasizing the spectral fine structure of speech signals. To improve the subjective quality of synthesized speech, the difference between synthesized and actual speech was established by calculating the distance in the perceptual domains instead of using the conventional mean square error (MSE). Two deep neural networks (DNNs) were employed to separately estimate the speech spectra and the filter coefficients of HE, connected in a cascading manner. The DNNs were trained to incrementally and iteratively minimize both the MSE and the perceptual distance (PD). A feasibility test showed that the perceptual evaluation of speech quality (PESQ) and the short-time objective intelligibility measure (STOI) were improved by 17.8 and 2.9%, respectively, compared with previous methods. Subjective listening tests revealed that the proposed method yielded perceptually preferred results compared with that of the conventional MSE-based method.

scholarly journals Voice Conversion Using a Perceptual Criterion

2020 ◽  
Vol 10 (8) ◽  
pp. 2884
Author(s):  
Ki-Seung Lee
Keyword(s):  
Voice Conversion ◽  
Spectral Envelope ◽  
Perceptual Quality ◽  
Speech Signals ◽  
Perceptual Evaluation ◽  
Perceptual Distance ◽  
Modification Factor ◽  
Maximum Improvement ◽  
Validation Tests ◽  
Conversion Rules

In voice conversion (VC), it is highly desirable to obtain transformed speech signals that are perceptually close to a target speaker’s voice. To this end, a perceptually meaningful criterion where the human auditory system was taken into consideration in measuring the distances between the converted and the target voices was adopted in the proposed VC scheme. The conversion rules for the features associated with the spectral envelope and the pitch modification factor were jointly constructed so that perceptual distance measurement was minimized. This minimization problem was solved using a deep neural network (DNN) framework where input features and target features were derived from source speech signals and time-aligned version of target speech signals, respectively. The validation tests were carried out for the CMU ARCTIC database to evaluate the effectiveness of the proposed method, especially in terms of perceptual quality. The experimental results showed that the proposed method yielded perceptually preferred results compared with independent conversion using conventional mean-square error (MSE) criterion. The maximum improvement in perceptual evaluation of speech quality (PESQ) was 0.312, compared with the conventional VC method.

Destruction of Actin Filaments by Osmium Tetroxide

1977 ◽  
Vol 35 ◽  
pp. 466-467
Author(s):  
P. Maupin-Szamier ◽  
T. D. Pollard
Keyword(s):  
Actin Filaments ◽  
Time Course ◽  
Osmium Tetroxide ◽  
Rabbit Muscle ◽  
Muscle Actin ◽  
Sodium Phosphate Buffer ◽  
Transmission Electron ◽  
The Difference ◽  
Rates Of Decay ◽  
Short Time

We have studied the destruction of rabbit muscle actin filaments by osmium tetroxide (OSO4) to develop methods which will preserve the structure of actin filaments during preparation for transmission electron microscopy.Negatively stained F-actin, which appears as smooth, gently curved filaments in control samples (Fig. 1a), acquire an angular, distorted profile and break into progressively shorter pieces after exposure to OSO4 (Fig. 1b,c). We followed the time course of the reaction with viscometry since it is a simple, quantitative method to assess filament integrity. The difference in rates of decay in viscosity of polymerized actin solutions after the addition of four concentrations of OSO4 is illustrated in Fig. 2. Viscometry indicated that the rate of actin filament destruction is also dependent upon temperature, buffer type, buffer concentration, and pH, and requires the continued presence of OSO4. The conditions most favorable to filament preservation are fixation in a low concentration of OSO4 for a short time at 0°C in 100mM sodium phosphate buffer, pH 6.0.

Evaluation of a Silent Speech Interface Based on Magnetic Sensing and Deep Learning for a Phonetically Rich Vocabulary

2017 ◽  
Author(s):  
Jose A. Gonzalez ◽  
Lam A. Cheah ◽  
Phil D. Green ◽  
James M. Gilbert ◽  
Stephen R. Ell ◽  
...  
Keyword(s):  
Deep Learning ◽  
Magnetic Sensing ◽  
Speech Interface ◽  
Silent Speech

Evaluation of a silent speech interface based on magnetic sensing

2010 ◽  
Author(s):  
Robin Hofe ◽  
Stephen R. Ell ◽  
Michael J. Fagan ◽  
James M. Gilbert ◽  
Phil D. Green ◽  
...  
Keyword(s):  
Magnetic Sensing ◽  
Speech Interface ◽  
Silent Speech

Modification of Speech Discrimination in Patients with Binaural Asymmetrical Hearing Loss

1971 ◽  
Vol 36 (2) ◽  
pp. 208-212 ◽  
Author(s):  
Herbert J. Arkebauer ◽  
George T. Mencher ◽  
Carol McCall
Keyword(s):  
Hearing Loss ◽  
Sound Field ◽  
Combined Effect ◽  
Speech Signals ◽  
Speech Discrimination ◽  
The Difference ◽  
Better Than

Ten patients with bilateral asymmetrical hearing losses were tested for differences in speech discrimination scores under the following listening conditions: poorer ear under earphone; better ear under earphone; sound field, ears unoccluded; and sound field, poorer ear occluded. A patient manifesting a bilateral asymmetrical hearing loss may not be able to either separate or integrate two speech signals; however, occlusion of the poorer ear may be an advantageous means of obtaining maximum speech discrimination. Examination of the speech discrimination scores indicates the existence of detrimental interaction between ears exhibiting bilateral asymmetrical hearing loss. These findings also indicate that when the difference between ears is greater, speech discrimination is better than when asymmetry approximates symmetry. Apparently, the greater the impairment in the better ear, the greater the results to be gained by occluding the poorer ear. These findings were interpreted as being relevant in determining candidacy for binaural amplification. Such candidacy should be determined on the basis of speech discrimination scores obtained from each ear independently, and the combined effect of both aids.

Small-vocabulary speech recognition using a silent speech interface based on magnetic sensing

2013 ◽  
Vol 55 (1) ◽  
pp. 22-32 ◽  
Author(s):  
Robin Hofe ◽  
Stephen R. Ell ◽  
Michael J. Fagan ◽  
James M. Gilbert ◽  
Phil D. Green ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Magnetic Sensing ◽  
Speech Interface ◽  
Silent Speech

The Informal Use of Time as a Component of Multicultural Regional Identity in Transcarpathia (Ukraine)

2021 ◽  
Vol 48 (1) ◽  
pp. 73-102
Author(s):  
Csilla Fedinec ◽  
István Csernicskó
Keyword(s):  
Soviet Union ◽  
Local Time ◽  
Regional Identity ◽  
Point Of View ◽  
Sociological Research ◽  
Time Zone ◽  
Use Of Time ◽  
The Soviet Union ◽  
The Difference ◽  
Short Time

Abstract Based on the data of sociological research, the analysis of the linguistic landscapes of Transcarpathian cities, and quotations from travel guides, this paper illustrates that in Transcarpathia, a significant part of the population—regardless of ethnicity—live their lives not according to the official Kyiv time (eet), but according to the local time (cet). The difference between official centralized time and “local time” appeared in Transcarpathia when the region became annexed to the Soviet Union. Yet before the Second World War, each state in the region used Central European time. The Soviet regime introduced msk, which was two hours ahead. The distinction between “local time” and central time has been maintained since Transcarpathia became part of the newly independent Ukraine. The population of the region has been urged to use a different time zone for a relatively short time from a historical point of view. The persistence of “local time” is also strengthened by the fact that it contributes to the image of Transcarpathia as a particular, specific region of Ukraine. “Local time” in Transcarpathia has become part of the region’s tourism brand.

Sign in / Sign up

Export Citation Format

Share Document