Classification of voice disorder in children with cochlear implantation and hearing aid using multiple classifier fusion

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.

Systematic analysis of the benefits of cochlear implants on voice production

PURPOSE

To perform a systematic analysis of the research regarding vocal characteristics of hearing impaired children or adults with cochlear implants.

RESEARCH STRATEGY

A literature search was conducted in the databases Web of Science, Bireme, and Universidade de São Paulo's and CAPES' thesis and dissertations databases using the keywords voice, voice quality, and cochlear implantation, and their respective correspondents in Brazilian Portuguese.

SELECTION CRITERIA

The selection criteria included: title consistent with the purpose of this review; participants necessarily being children or adults with severe to profound pre-lingual or post-lingual hearing loss using cochlear implants; and data regarding participants' performance on perception and/or acoustic analysis of the voice.

RESULTS

Twenty seven papers were classified according to the levels of evidence and quality indicators recommended by the American Speech-Language-Hearing Association (ASHA). The designs of the studies were considered of low and medium levels of evidence. Six papers were classified as IIb, 20 as III, and one as IV.

CONCLUSION

The voice of hearing impaired children and adults with cochlear implants has been little studied. There is not an effective number of studies with high evidence levels which precisely show the effects of the cochlear implantation on the quality of voice of these individuals.

Cochlear implanted children present vocal parameters within normal standards

OBJECTIVE

to compare acoustic and perceptual parameters regarding the voice of cochlear implanted children, with normal hearing children.

METHOD

this is a cross-sectional, quantitative and qualitative study.

METHODS

Thirty six cochlear implanted children aged between 3 y and 3 m to 5 y and 9 m and 25 children with normal hearing, aged between 3 y and 11 m and 6 y and 6 m, participated in this study. The recordings and the acoustics analysis of the sustained vowel/a/and spontaneous speech were performed using the PRAAT program. The parameters analyzed for the sustained vowel were the mean of the fundamental frequency, jitter, shimmer and harmonic-to-noise ratio (HNR). For the spontaneous speech, the minimum and maximum frequencies and the number of semitones were extracted. The perceptual analysis of the speech material was analyzed using visual-analogical scales of 100 points, composing the aspects related to the overall severity of the vocal deviation, roughness, breathiness, strain, pitch, loudness and resonance deviation, and instability. This last parameter was only analyzed for the sustained vowel.

RESULTS

The results demonstrated that the majority of the vocal parameters analyzed in the samples of the implanted children disclosed values similar to those obtained by the group of children with normal hearing.

CONCLUSION

implanted children who participate in a (re) habilitation and follow-up program, can present vocal characteristics similar to those vocal characteristics of children with normal hearing.

Real-time feature extraction of P300 component using adaptive nonlinear principal component analysis

BACKGROUND

The electroencephalography (EEG) signals are known to involve the firings of neurons in the brain. The P300 wave is a high potential caused by an event-related stimulus. The detection of P300s included in the measured EEG signals is widely investigated. The difficulties in detecting them are that they are mixed with other signals generated over a large brain area and their amplitudes are very small due to the distance and resistivity differences in their transmittance.

METHODS

A novel real-time feature extraction method for detecting P300 waves by combining an adaptive nonlinear principal component analysis (ANPCA) and a multilayer neural network is proposed. The measured EEG signals are first filtered using a sixth-order band-pass filter with cut-off frequencies of 1 Hz and 12 Hz. The proposed ANPCA scheme consists of four steps: pre-separation, whitening, separation, and estimation. In the experiment, four different inter-stimulus intervals (ISIs) are utilized: 325 ms, 350 ms, 375 ms, and 400 ms.

RESULTS

The developed multi-stage principal component analysis method applied at the pre-separation step has reduced the external noises and artifacts significantly. The introduced adaptive law in the whitening step has made the subsequent algorithm in the separation step to converge fast. The separation performance index has varied from -20 dB to -33 dB due to randomness of source signals. The robustness of the ANPCA against background noises has been evaluated by comparing the separation performance indices of the ANPCA with four algorithms (NPCA, NSS-JD, JADE, and SOBI), in which the ANPCA algorithm demonstrated the shortest iteration time with performance index about 0.03. Upon this, it is asserted that the ANPCA algorithm successfully separates mixed source signals.

CONCLUSIONS

The independent components produced from the observed data using the proposed method illustrated that the extracted signals were clearly the P300 components elicited by task-related stimuli. The experiment using 350 ms ISI showed the best performance. Since the proposed method does not use down-sampling and averaging, it can be used as a viable tool for real-time clinical applications.