scholarly journals Unifying information theory and machine learning in a model of electrode discrimination in cochlear implants

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0257568
Author(s):  
Xiao Gao ◽  
David Grayden ◽  
Mark McDonnell
Keyword(s):  
Machine Learning ◽  
Information Theory ◽  
Speech Recognition ◽  
Speech Perception ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Key Factors ◽  
Discrimination Ability ◽  
Individual Level ◽  
Subject Variability

Despite the development and success of cochlear implants over several decades, wide inter-subject variability in speech perception is reported. This suggests that cochlear implant user-dependent factors limit speech perception at the individual level. Clinical studies have demonstrated the importance of the number, placement, and insertion depths of electrodes on speech recognition abilities. However, these do not account for all inter-subject variability and to what extent these factors affect speech recognition abilities has not been studied. In this paper, an information theoretic method and machine learning technique are unified in a model to investigate the extent to which key factors limit cochlear implant electrode discrimination. The framework uses a neural network classifier to predict which electrode is stimulated for a given simulated activation pattern of the auditory nerve, and mutual information is then estimated between the actual stimulated electrode and predicted ones. We also investigate how and to what extent the choices of parameters affect the performance of the model. The advantages of this framework include i) electrode discrimination ability is quantified using information theory, ii) it provides a flexible framework that may be used to investigate the key factors that limit the performance of cochlear implant users, and iii) it provides insights for future modeling studies of other types of neural prostheses.

Improving Speech Perception in Noise for Children with Cochlear Implants

2011 ◽  
Vol 22 (09) ◽  
pp. 623-632 ◽  
Author(s):  
René H. Gifford ◽  
Amy P. Olund ◽  
Melissa DeJong
Keyword(s):  
Speech Recognition ◽  
Speech Perception ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Repeated Measures ◽  
Background Noise ◽  
Normal Hearing ◽  
Speech Understanding ◽  
The Mean ◽  
Experimental Subjects

Background: Current cochlear implant recipients are achieving increasingly higher levels of speech recognition; however, the presence of background noise continues to significantly degrade speech understanding for even the best performers. Newer generation Nucleus cochlear implant sound processors can be programmed with SmartSound strategies that have been shown to improve speech understanding in noise for adult cochlear implant recipients. The applicability of these strategies for use in children, however, is not fully understood nor widely accepted. Purpose: To assess speech perception for pediatric cochlear implant recipients in the presence of a realistic restaurant simulation generated by an eight-loudspeaker (R-SPACE™) array in order to determine whether Nucleus sound processor SmartSound strategies yield improved sentence recognition in noise for children who learn language through the implant. Research Design: Single subject, repeated measures design. Study Sample: Twenty-two experimental subjects with cochlear implants (mean age 11.1 yr) and 25 control subjects with normal hearing (mean age 9.6 yr) participated in this prospective study. Intervention: Speech reception thresholds (SRT) in semidiffuse restaurant noise originating from an eight-loudspeaker array were assessed with the experimental subjects’ everyday program incorporating Adaptive Dynamic Range Optimization (ADRO) as well as with the addition of Autosensitivity control (ASC). Data Collection and Analysis: Adaptive SRTs with the Hearing In Noise Test (HINT) sentences were obtained for all 22 experimental subjects, and performance—in percent correct—was assessed in a fixed +6 dB SNR (signal-to-noise ratio) for a six-subject subset. Statistical analysis using a repeated-measures analysis of variance (ANOVA) evaluated the effects of the SmartSound setting on the SRT in noise. Results: The primary findings mirrored those reported previously with adult cochlear implant recipients in that the addition of ASC to ADRO significantly improved speech recognition in noise for pediatric cochlear implant recipients. The mean degree of improvement in the SRT with the addition of ASC to ADRO was 3.5 dB for a mean SRT of 10.9 dB SNR. Thus, despite the fact that these children have acquired auditory/oral speech and language through the use of their cochlear implant(s) equipped with ADRO, the addition of ASC significantly improved their ability to recognize speech in high levels of diffuse background noise. The mean SRT for the control subjects with normal hearing was 0.0 dB SNR. Given that the mean SRT for the experimental group was 10.9 dB SNR, despite the improvements in performance observed with the addition of ASC, cochlear implants still do not completely overcome the speech perception deficit encountered in noisy environments accompanying the diagnosis of severe-to-profound hearing loss. Conclusion: SmartSound strategies currently available in latest generation Nucleus cochlear implant sound processors are able to significantly improve speech understanding in a realistic, semidiffuse noise for pediatric cochlear implant recipients. Despite the reluctance of pediatric audiologists to utilize SmartSound settings for regular use, the results of the current study support the addition of ASC to ADRO for everyday listening environments to improve speech perception in a child's typical everyday program.

scholarly journals Auditory Speech Perception Development in Relation to Patient's Age with Cochlear Implant

2016 ◽  
Vol 21 (03) ◽  
pp. 206-212 ◽  
Author(s):  
Grace Ciscare ◽  
Erika Mantello ◽  
Carla Fortunato-Queiroz ◽  
Miguel Hyppolito ◽  
Ana Reis
Keyword(s):  
Speech Perception ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Statistical Difference ◽  
Hearing Aid ◽  
Age Groups ◽  
Auditory Thresholds ◽  
Caregiver Education ◽  
Auditory Speech ◽  
Hearing Aid Use

Introduction A cochlear implant in adolescent patients with pre-lingual deafness is still a debatable issue. Objective The objective of this study is to analyze and compare the development of auditory speech perception in children with pre-lingual auditory impairment submitted to cochlear implant, in different age groups in the first year after implantation. Method This is a retrospective study, documentary research, in which we analyzed 78 reports of children with severe bilateral sensorineural hearing loss, unilateral cochlear implant users of both sexes. They were divided into three groups: G1, 22 infants aged less than 42 months; G2, 28 infants aged between 43 to 83 months; and G3, 28 older than 84 months. We collected medical record data to characterize the patients, auditory thresholds with cochlear implants, assessment of speech perception, and auditory skills. Results There was no statistical difference in the association of the results among groups G1, G2, and G3 with sex, caregiver education level, city of residence, and speech perception level. There was a moderate correlation between age and hearing aid use time, age and cochlear implants use time. There was a strong correlation between age and the age cochlear implants was performed, hearing aid use time and age CI was performed. Conclusion There was no statistical difference in the speech perception in relation to the patient's age when cochlear implant was performed. There were statistically significant differences for the variables of auditory deprivation time between G3 - G1 and G2 - G1 and hearing aid use time between G3 - G2 and G3 - G1.

scholarly journals Mismatch Negativity in Children with Cochlear Implant

2019 ◽  
Vol 23 (03) ◽  
pp. e292-e298
Author(s):  
Natalia Martinez Fernandes ◽  
Daniela Gil ◽  
Marisa Frasson de Azevedo
Keyword(s):  
Speech Perception ◽  
Language Development ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Family Involvement ◽  
Mismatch Negativity ◽  
Control Group ◽  
Study Group ◽  
Cross Sectional ◽  
Hearing Children

Introduction The mismatch negativity (MMN) is a negative long-latency auditory potential elicited by any discriminable change in a repetitive aspect of auditory stimulation. This evoked potential can provide cortical information about the sound processing, including in children who use cochlear implants. Objective To identify MMN characteristics regarding latency, amplitude, and wave area in cochlear implanted children and to identify associations among language development, speech perception and family involvement. Methods This is a descriptive, observational, cross-sectional study, which compared two groups: study group—children with cochlear implant, and control group—hearing children. The children were submitted to MMN evaluation with non-verbal tone burst stimulus, differing in frequency in sound field at 70 dBHL, with SmartEP equipment (Intelligent Hearing Systems, Miami, FL, USA). Speech perception and language development questionnaires were also applied, and the family participation in the rehabilitation process was classified. Results The occurrence of MMN was 73.3% for the control group and 53.3% for the study group. Values of latency, amplitude and area of MMN of children using cochlear implants were similar to those of hearing children, and did not differ between groups. The occurrence of MMN was not correlated to the variables of hearing, language and family categories. Conclusion Children with cochlear implants showed similar MMN responses to those of the children in the control group, with mean latency, amplitude and area of 208.9 ms (±12.8), -2.37 μV (±0.38) and 86.5 μVms (±23.4), respectively. There was no correlation between the presence of MMN and children's performance in the auditory and language development tests or family involvement during rehabilitation.

Speech Perception with a Single-Channel Cochlear Implant

1990 ◽  
Vol 33 (2) ◽  
pp. 229-237 ◽  
Author(s):  
Arlene Earley Carney ◽  
Marjorie Kienle ◽  
Richard T. Miyamoto
Keyword(s):  
Speech Perception ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Single Channel ◽  
Performance Level ◽  
The Subject ◽  
Overall Performance

Suprasegmental and segmental speech perception tasks were administered to 8 patients with single-channel cochlear implants. Suprasegmental tasks included the recognition of syllable number, syllabic stress, and intonation. Segmental tasks included the recognition of vowels and consonants in three modalities: visual only, implant only, and visual + implant. Results were compared to those obtained from artificially deafened adults using a single-channel vibrotactile device (Carney, 1988; Carney & Beachler, 1986). The patterns of responses for both suprasegmental and segmental tasks were highly similar for both groups of subjects, despite differences between the characteristics of the subject samples. These results suggest that single-channel sensory devices, whether they be cochlear implants or vibrotactile aids, produce similar patterns of speech perception errors, even when differences are observed in overall performance level.

Effect of Frequency Boundary Assignment on Speech Recognition with the Nucleus 24 ACE Speech Coding Strategy

2007 ◽  
Vol 18 (08) ◽  
pp. 700-717 ◽  
Author(s):  
Marios S. Fourakis ◽  
John W. Hawks ◽  
Laura K. Holden ◽  
Margaret W. Skinner ◽  
Timothy A. Holden
Keyword(s):  
Speech Recognition ◽  
Speech Perception ◽  
Cochlear Implants ◽  
Speech Coding ◽  
Frequency Assignment ◽  
Speech Stimuli ◽  
Unlimited Number ◽  
Coding Strategy ◽  
Technological Limitations ◽  
Nucleus 24

The choice of frequency boundaries for the analysis channels of cochlear implants has been shown to impact the speech perception performance of adult recipients (Skinner et al, 1995; Fourakis et al, 2004). While technological limitations heretofore have limited the clinical feasibility of investigating novel frequency assignments, the SPEAR3 research processor affords the opportunity to investigate an unlimited number of possibilities. Here, four different assignments are evaluated using a variety of speech stimuli. All participants accommodated to assignment changes, and no one assignment was significantly preferred. The results suggest that better performance can be achieved using a strategy whereby (1) there are at least 7-8 electrodes allocated below 1000 Hz, (2) the majority of remaining electrodes are allocated between 1100 - 3000 Hz, and (3) the region above 3 kHz is represented by relatively few electrodes (i.e., 1-3). The results suggest that such frequency assignment flexibility should be made clinically available. La escogencia de límites de frecuencia para los canales de análisis de los implantes cocleares se ha visto que impacta el desempeño en la percepción del lenguaje de adultos implantados (Skinner y col, 1995; Fourakis y col, 2004). Mientras que las limitaciones tecnológicas hasta este momento han restringido la factibilidad clínica de investigar nuevas asignaciones de frecuencia, el procesador experimental SPEAR3 ofrece la oportunidad de investigar un número ilimitado de posibilidades. Aquí, se evalúan cuatro asignaciones diferentes utilizando una variedad de estímulos de lenguaje. Todos los participantes se acomodaron a los cambios de asignación y ninguna asignación tuvo una preferencia significativa. Los resultados sugieren que puede obtenerse un desempeño mejor utilizando una estrategia donde (1) existan al menos 7-8 electrodos colocados por debajo de 1000 Hz, (2) la mayoría de los electrodos remanentes sean colocados entre 1100 – 3000 Hz, y (3) la región por encima de 3 kHz esté representada por relativamente pocos electrodos (p.e., 1-3). Los resultados sugieren que tal flexibilidad en la asignación de frecuencias debería estar clínicamente disponible.

scholarly journals Speech Perception for Adult Cochlear Implant Recipients in a Realistic Background Noise: Effectiveness of Preprocessing Strategies and External Options for Improving Speech Recognition in Noise

2010 ◽  
Vol 21 (07) ◽  
pp. 441-451 ◽  
Author(s):  
René H. Gifford ◽  
Lawrence J. Revit
Keyword(s):  
Speech Recognition ◽  
Speech Perception ◽  
Cochlear Implant ◽  
Repeated Measures ◽  
Recognition Performance ◽  
Single Subject ◽  
Repeated Measures Design ◽  
Listening Environments ◽  
Improved Performance ◽  
Listening In Noise

Background: Although cochlear implant patients are achieving increasingly higher levels of performance, speech perception in noise continues to be problematic. The newest generations of implant speech processors are equipped with preprocessing and/or external accessories that are purported to improve listening in noise. Most speech perception measures in the clinical setting, however, do not provide a close approximation to real-world listening environments. Purpose: To assess speech perception for adult cochlear implant recipients in the presence of a realistic restaurant simulation generated by an eight-loudspeaker (R-SPACE™) array in order to determine whether commercially available preprocessing strategies and/or external accessories yield improved sentence recognition in noise. Research Design: Single-subject, repeated-measures design with two groups of participants: Advanced Bionics and Cochlear Corporation recipients. Study Sample: Thirty-four subjects, ranging in age from 18 to 90 yr (mean 54.5 yr), participated in this prospective study. Fourteen subjects were Advanced Bionics recipients, and 20 subjects were Cochlear Corporation recipients. Intervention: Speech reception thresholds (SRTs) in semidiffuse restaurant noise originating from an eight-loudspeaker array were assessed with the subjects' preferred listening programs as well as with the addition of either Beam™ preprocessing (Cochlear Corporation) or the T-Mic® accessory option (Advanced Bionics). Data Collection and Analysis: In Experiment 1, adaptive SRTs with the Hearing in Noise Test sentences were obtained for all 34 subjects. For Cochlear Corporation recipients, SRTs were obtained with their preferred everyday listening program as well as with the addition of Focus preprocessing. For Advanced Bionics recipients, SRTs were obtained with the integrated behind-the-ear (BTE) mic as well as with the T-Mic. Statistical analysis using a repeated-measures analysis of variance (ANOVA) evaluated the effects of the preprocessing strategy or external accessory in reducing the SRT in noise. In addition, a standard t-test was run to evaluate effectiveness across manufacturer for improving the SRT in noise. In Experiment 2, 16 of the 20 Cochlear Corporation subjects were reassessed obtaining an SRT in noise using the manufacturer-suggested “Everyday,” “Noise,” and “Focus” preprocessing strategies. A repeated-measures ANOVA was employed to assess the effects of preprocessing. Results: The primary findings were (i) both Noise and Focus preprocessing strategies (Cochlear Corporation) significantly improved the SRT in noise as compared to Everyday preprocessing, (ii) the T-Mic accessory option (Advanced Bionics) significantly improved the SRT as compared to the BTE mic, and (iii) Focus preprocessing and the T-Mic resulted in similar degrees of improvement that were not found to be significantly different from one another. Conclusion: Options available in current cochlear implant sound processors are able to significantly improve speech understanding in a realistic, semidiffuse noise with both Cochlear Corporation and Advanced Bionics systems. For Cochlear Corporation recipients, Focus preprocessing yields the best speech-recognition performance in a complex listening environment; however, it is recommended that Noise preprocessing be used as the new default for everyday listening environments to avoid the need for switching programs throughout the day. For Advanced Bionics recipients, the T-Mic offers significantly improved performance in noise and is recommended for everyday use in all listening environments.

scholarly journals A Longitudinal Study in Adults With Sequential Bilateral Cochlear Implants: Time Course for Individual Ear and Bilateral Performance

2014 ◽  
Vol 57 (3) ◽  
pp. 1108-1126 ◽  
Author(s):  
Ruth M. Reeder ◽  
Jill B. Firszt ◽  
Laura K. Holden ◽  
Michael J. Strube
Keyword(s):  
Longitudinal Study ◽  
Speech Recognition ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Time Course ◽  
Performance Outcomes ◽  
Prospective Longitudinal Study ◽  
Early Improvement ◽  
Prospective Longitudinal ◽  
The Impact

PurposeThe purpose of this study was to examine the rate of progress in the 2nd implanted ear as it relates to the 1st implanted ear and to bilateral performance in adult sequential cochlear implant recipients. In addition, this study aimed to identify factors that contribute to patient outcomes.MethodThe authors performed a prospective longitudinal study in 21 adults who received bilateral sequential cochlear implants. Testing occurred at 6 intervals: prebilateral through 12 months postbilateral implantation. Measures evaluated speech recognition in quiet and noise, localization, and perceived benefit.ResultsSecond ear performance was similar to 1st ear performance by 6 months postbilateral implantation. Bilateral performance was generally superior to either ear alone; however, participants with shorter 2nd ear length of deafness (<20 years) had more rapid early improvement and better overall outcomes than those with longer 2nd ear length of deafness (>30 years). All participants reported bilateral benefit.ConclusionsAdult cochlear implant recipients demonstrated benefit from 2nd ear implantation for speech recognition, localization, and perceived communication function. Because performance outcomes were related to length of deafness, shorter time between surgeries may be warranted to reduce negative length-of-deafness effects. Future study may clarify the impact of other variables, such as preimplant hearing aid use, particularly for individuals with longer periods of deafness.

Speech Perception Performance in Experienced Cochlear-Implant Patients Receiving the SPEAK Processing Strategy in the Nucleus Spectra-22 Cochlear Implant

1998 ◽  
Vol 41 (5) ◽  
pp. 1073-1087 ◽  
Author(s):  
Aaron J. Parkinson ◽  
Wendy S. Parkinson ◽  
Richard S. Tyler ◽  
Mary W. Lowder ◽  
Bruce J. Gantz
Keyword(s):  
Speech Recognition ◽  
Speech Perception ◽  
Cochlear Implant ◽  
Sound Quality ◽  
Learning Effects ◽  
Processing Strategy ◽  
Subjective Ratings ◽  
Open Set ◽  
Wide Range

Sixteen experienced cochlear implant patients with a wide range of speechperception abilities received the SPEAK processing strategy in the Nucleus Spectra-22 cochlear implant. Speech perception was assessed in quiet and in noise with SPEAK and with the patients' previous strategies (for most, Multipeak) at the study onset, as well as after using SPEAK for 6 months. Comparisons were made within and across the two test sessions to elucidate possible learning effects. Patients were also asked to rate the strategies on seven speech recognition and sound quality scales. After 6 months' experience with SPEAK, patients showed significantly improved mean performance on a range of speech recognition measures in quiet and noise. When mean subjective ratings were compared over time there were no significant differences noted between strategies. However, many individuals rated the SPEAK strategy better for two or more of the seven subjective measures. Ratings for "appreciation of music" and "quality of my own voice" in particular were generally higher for SPEAK. Improvements were realized by patients with a wide range of speech perception abilities, including those with little or no open-set speech recognition.

scholarly journals An Attempt to Improve Bilateral Cochlear Implants by Increasing the Distance between Electrodes and Providing Complementary Information to the Two Ears

2010 ◽  
Vol 21 (01) ◽  
pp. 052-065 ◽  
Author(s):  
Richard S. Tyler ◽  
Shelley A. Witt ◽  
Camille C. Dunn ◽  
Ann Perreau ◽  
Aaron J. Parkinson ◽  
...  
Keyword(s):  
Speech Perception ◽  
Cochlear Implant ◽  
Cochlear Implants ◽  
Speech Processing ◽  
Processing Strategy ◽  
Bilateral Cochlear Implants ◽  
Channel Interaction ◽  
Consonant Recognition ◽  
Bilateral Cochlear Implant ◽  
Input Spectrum

Objectives: The purpose of this investigation was to determine if adult bilateral cochlear implant recipients could benefit from using a speech processing strategy in which the input spectrum was interleaved among electrodes across the two implants. Design: Two separate experiments were conducted. In both experiments, subjects were tested using a control speech processing strategy and a strategy in which the full input spectrum was filtered so that only the output of half of the filters was audible to one implant, while the output of the alternative filters was audible to the other implant. The filters were interleaved in a way that created alternate frequency “holes” between the two cochlear implants. Results: In experiment one, four subjects were tested on consonant recognition. Results indicated that one of the four subjects performed better with the interleaved strategy, one subject received a binaural advantage with the interleaved strategy that they did not receive with the control strategy, and two subjects showed no decrement in performance when using the interleaved strategy. In the second experiment, 11 subjects were tested on word recognition, sentences in noise, and localization (it should be noted that not all subjects participated in all tests). Results showed that for speech perception testing one subject achieved significantly better scores with the interleaved strategy on all tests, and seven subjects showed a significant improvement with the interleaved strategy on at least one test. Only one subject showed a decrement in performance on all speech perception tests with the interleaved strategy. Out of nine subjects, one subject preferred the sound quality of the interleaved strategy. No one performed better on localization with the interleaved strategy. Conclusion: Data from this study indicate that some adult bilateral cochlear implant recipients can benefit from using a speech processing strategy in which the input spectrum is interleaved among electrodes across the two implants. It is possible that the subjects in this study who showed a significant improvement with the interleaved strategy did so because of less channel interaction; however, this hypothesis was not directly tested.

Sign in / Sign up

Export Citation Format

Share Document