Deniz Başkent

Bio: Deniz Başkent is an academic researcher from University Medical Center Groningen. The author has contributed to research in topics: Speech perception & Intelligibility (communication). The author has an hindex of 32, co-authored 125 publications receiving 3827 citations. Previous affiliations of Deniz Başkent include University of Southern California & Bilkent University.

Speech recognition in noise as a function of the number of spectral channels: Comparison of acoustic hearing and cochlear implants

Abstract: Speech recognition was measured as a function of spectral resolution (number of spectral channels) and speech-to-noise ratio in normal-hearing (NH) and cochlear-implant(CI) listeners. Vowel, consonant, word, and sentence recognition were measured in five normal-hearing listeners, ten listeners with the Nucleus-22 cochlear implant, and nine listeners with the Advanced Bionics Clarion cochlear implant. Recognition was measured as a function of the number of spectral channels (noise bands or electrodes) at signal-to-noise ratios of +15, +10, +5, 0 dB, and in quiet. Performance with three different speech processing strategies (SPEAK, CIS, and SAS) was similar across all conditions, and improved as the number of electrodes increased (up to seven or eight) for all conditions. For all noise levels, vowel and consonant recognition with the SPEAK speech processor did not improve with more than seven electrodes, while for normal-hearing listeners, performance continued to increase up to at least 20 channels. Speech recognition on more difficult speech materials (word and sentence recognition) showed a marginally significant increase in Nucleus-22 listeners from seven to ten electrodes. The average implant score on all processing strategies was poorer than scores of NH listeners with similar processing. However, the best CI scores were similar to the normal-hearing scores for that condition (up to seven channels). CI listeners with the highest performance level increased in performance as the number of electrodes increased up to seven, while CI listeners with low levels of speech recognition did not increase in performance as the number of electrodes was increased beyond four. These results quantify the effect of number of spectral channels on speech recognition in noise and demonstrate that most CI subjects are not able to fully utilize the spectral information provided by the number of electrodes used in their implant.

Factors Affecting Auditory Performance of Postlinguistically Deaf Adults Using Cochlear Implants: An Update with 2251 Patients

Abstract: Objective: To update a 15-year-old study of 800 postlinguistically deaf adult patients showing how duration of severe to profound hearing loss, age at cochlear implantation (CI), age at onset of severe to profound hearing loss, etiology and CI experience affected CI outcome. Study Design: Retrospective multicenter study. Methods: Data from 2251 adult patients implanted since 2003 in 15 international centers were collected and speech scores in quiet were converted to percentile ranks to remove differences between centers. Results: The negative effect of long duration of severe to profound hearing loss was less important in the new data than in 1996; the effects of age at CI and age at onset of severe to profound hearing loss were delayed until older ages; etiology had a smaller effect, and the effect of CI experience was greater with a steeper learning curve. Patients with longer durations of severe to profound hearing loss were less likely to improve with CI experience than patients with shorter duration of severe to profound hearing loss. Conclusions: The factors that were relevant in 1996 were still relevant in 2011, although their relative importance had changed. Relaxed patient selection criteria, improved clinical management of hearing loss, modifications of surgical practice, and improved devices may explain the differences.

Pre-, Per- and Postoperative Factors Affecting Performance of Postlinguistically Deaf Adults Using Cochlear Implants: A New Conceptual Model over Time

Abstract: Objective: To test the influence of multiple factors on cochlear implant (CI) speech performance in quiet and in noise for postlinguistically deaf adults, and to design a model of predicted auditory performance with a CI as a function of the significant factors. Study Design: Retrospective multi-centre study. Methods: Data from 2251 patients implanted since 2003 in 15 international centres were collected. Speech scores in quiet and in noise were converted into percentile ranks to remove differences between centres. The influence of 15 pre-, per- and postoperative factors, such as the duration of moderate hearing loss (mHL), the surgical approach (cochleostomy or round window approach), the angle of insertion, the percentage of active electrodes, and the brand of device were tested. The usual factors, duration of profound HL (pHL), age, etiology, duration of CI experience, that are already known to have an influence, were included in the statistical analyses. Results: The significant factors were: the pure tone average threshold of the better ear, the brand of device, the percentage of active electrodes, the use of hearing aids (HAs) during the period of pHL, and the duration of mHL. Conclusions: A new model was designed showing a decrease of performance that started during the period of mHL, and became faster during the period of pHL. The use of bilateral HAs slowed down the related central reorganization that is the likely cause of the decreased performance.

Interactions between cochlear implant electrode insertion depth and frequency-place mapping.

Abstract: While new electrode designs allow deeper insertion and wider coverage in the cochlea, there is still considerable variation in the insertion depth of the electrode array among cochlear implant users. The present study measures speech recognition as a function of insertion depth, varying from a deep insertion of 10 electrodes at 28.8 mm to a shallow insertion of a single electrode at 7.2 mm, in four Med-El Combi 40+ users. Short insertion depths were simulated by inactivating apical electrodes. Speech recognition increased with deeper insertion, reaching an asymptotic level at 21.6 or 26.4 mm depending on the frequency-place map used. Baskent and Shannon [J. Acoust. Soc. Am. 116, 3130–3140 (2004)] showed that speech recognition by implant users was best when the acoustic input frequency was matched onto the cochlear location that normally processes that frequency range, minimizing the spectral distortions in the map. However, if an electrode array is not fully inserted into the cochlea, a matched map will ...

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).