[A multiscale feature extraction algorithm for dysarthric speech recognition].

In this paper, we propose a multi-scale mel domain feature map extraction algorithm to solve the problem that the speech recognition rate of dysarthria is difficult to improve. We used the empirical mode decomposition method to decompose speech signals and extracted Fbank features and their first-order differences for each of the three effective components to construct a new feature map, which could capture details in the frequency domain. Secondly, due to the problems of effective feature loss and high computational complexity in the training process of single channel neural network, we proposed a speech recognition network model in this paper. Finally, training and decoding were performed on the public UA-Speech dataset. The experimental results showed that the accuracy of the speech recognition model of this method reached 92.77%. Therefore, the algorithm proposed in this paper can effectively improve the speech recognition rate of dysarthria.

Acoustic and kinematic analyses of Mandarin vowels in speakers with hearing impairment.

The central aim of this experiment was to compare acoustic parameters, formant frequencies and vowel space area (VSA), in adolescents with hearing-impaired (HI) and their normal-hearing (NH) peers; for kinematic parameters, the movements of vocal organs, especially the lips, jaw and tongue, during vowel production were analysed. The participants were 12 adolescents with different degrees of hearing impairment. The control group consisted of 12 age-matched NH adolescents. All participants were native Chinese speakers who were asked to produce the Mandarin vowels /a/, /i/ and /u/, with subsequent acoustic and kinematic analysis. There was significant difference between the two groups. Additionally, the HI group produced more exaggerated mouth and less tongue movements in all vowels, compared to their NH peers. Results were discussed regarding possible relationship between acoustic data, articulatory movements and degree of hearing loss to provide an integrative assessment of acoustic and kinematic characteristics of individuals with hearing loss.

[An acoustic-articulatory study of the nasal finals in students with and without hearing loss].

The central aim of this experiment was to compare the articulatory and acoustic characteristics of students with normal hearing (NH) and school aged children with hearing loss (HL), and to explore the articulatory-acoustic relations during the nasal finals. Fourteen HL and 10 control group were enrolled in this study, and the data of 4 HL students were removed because of their high pronunciation error rate. Data were collected using an electromagnetic articulography. The acoustic data and kinematics data of nasal finals were extracted by the phonetics and data processing software, and all data were analyzed by t test and correlation analysis. The paper shows that, the difference was statistically significant ( P<0.05 or P<0.01) in different vowels under the first two formant frequencies (F1, F2), the tongue position and the articulatory-acoustic relations between HL and NH group. The HL group's vertical movement data-F1 relations in /en/ and /eng/ are same as NH group. The conclusion of this study about participants with HL can provide support for speech healing training at increasing pronunciation accuracy in HL participants.

Research progress of diosgenin extraction from Dioscorea zingiberensis C. H. Wright: Inspiration of novel method with environmental protection and efficient characteristics.

Diosgenin was the starting materials to synthesize various hormone drugs and mainly generated from Dioscorea zingiberensis C. H. Wright by acidolysis, enzymolysis, microbiological fermentation, and integrated manner. Only acidic hydrolysis with strong acid such as hydrochloric acid or sulfuric acid was used in practice in diosgenin enterprises due to their feasibility and simplicity, nevertheless finally resulting in a great deal of unmanageable wastewater and severely polluted the surrounding environment. Aiming to provide a comprehensive and up-to date information of researches on diosgenin production from this plant, 151 cases were collected from scientific databases including Web of Science, Pubmed, Science Direct, Wiley, Springer, and China Knowledge Resource Integrated (CNKI). Their advantages and disadvantages with different production methods were analyzed based on these available data in this review paper. Considering the fact that nearly all of diosgenin enterprises were closed for the environmental protection and the life health of the people, this review paper was beneficial for providing useful guidelines to develop novel technologies with environmentally-friendly and cleaner features for diosgenin production or facilitate the transformation of other methods like enzymolysis, microbiological fermentation, or integrated methods from laboratory scale to industry scale.