检索结果-内蒙古大学图书馆

A Deep Denoising sound coding strategy for Cochlear Implants

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2023年第9期70卷 2700-2709页

作者： Gajecki, Tom Zhang, Yichi Nogueira, Waldo Med Univ Hannover & Cluster Excellence Dept Otolaryngol Hearing4all Hannover Germany Med Univ Hannover & Cluster Excellence Dept Otolaryngol Hearing4all D-30625 Hannover Germany

Cochlear implants (CIs) have proven to be successful at restoring the sensation of hearing in people who suffer from profound sensorineural hearing loss. CI users generally achieve good speech understanding in quiet acoustic conditions. However, their ability to understand speech degrades drastically when background interfering noise is present. To address this problem, current CI systems are delivered with front-end speech enhancement modules that can aid the listener in noisy environments. However, these only perform well under certain noisy conditions, leaving quite some room for improvement in more challenging circumstances. In this work, we propose replacing the CI sound coding strategy with a deep neural network (DNN) that performs end-to-end speech denoising by taking the raw audio as input and providing a denoised electrodogram, i.e., the electrical stimulation patterns applied to the electrodes across time. We specifically introduce a DNN that emulates a common CI sound coding strategy, the advanced combination encoder (ACE). We refer to the proposed algorithm as 'Deep ACE'. Deep ACE is designed not only to accurately code the acoustic signals in the same way that ACE would but also to automatically remove unwanted interfering noises, without sacrificing processing latency. The model was optimized using a CI-specific loss function and evaluated using objective measures as well as listening tests in CI participants. Results show that, based on objective measures, the proposed model achieved higher scores when compared to the baseline algorithms. Also, the proposed deep learning-based sound coding strategy gave eight CI users the highest speech intelligibility scores.

关键词： Speech enhancement Speech coding Electrodes Signal processing algorithms Wiener filters Noise measurement Decoding Cochlear implants sound coding strategy deep neural networks end-to-end speech enhancement

来源：评论

学校读者我要写书评

暂无评论

A Fused Deep Denoising sound coding strategy for Bilateral Cochlear Implants

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2024年第7期71卷 2232-2242页

作者： Gajecki, Tom Nogueira, Waldo Hannover Med Sch Dept Otolaryngol D-30625 Hannover Germany Cluster Excellence Hearing4all D-30625 Hannover Germany

Cochlear implants (CIs) provide a solution for individuals with severe sensorineural hearing loss to regain their hearing abilities. When someone experiences this form of hearing impairment in both ears, they may be equipped with two separate CI devices, which will typically further improve the CI benefits. This spatial hearing is particularly crucial when tackling the challenge of understanding speech in noisy environments, a common issue CI users face. Currently, extensive research is dedicated to developing algorithms that can autonomously filter out undesired background noises from desired speech signals. At present, some research focuses on achieving end-to-end denoising, either as an integral component of the initial CI signal processing or by fully integrating the denoising process into the CI sound coding strategy. This work is presented in the context of bilateral CI (BiCI) systems, where we propose a deep-learning-based bilateral speech enhancement model that shares information between both hearing sides. Specifically, we connect two monaural end-to-end deep denoising sound coding techniques through intermediary latent fusion layers. These layers amalgamate the latent representations generated by these techniques by multiplying them together, resulting in an enhanced ability to reduce noise and improve learning generalization. The objective instrumental results demonstrate that the proposed fused BiCI sound coding strategy achieves higher interaural coherence, superior noise reduction, and enhanced predicted speech intelligibility scores compared to the baseline methods. Furthermore, our speech-in-noise intelligibility results in BiCI users reveal that the deep denoising sound coding strategy can attain scores similar to those achieved in quiet conditions.

关键词： Encoding Noise reduction Auditory system Speech enhancement Particle separators Electrodes Data models Cochlear implants sound coding strategy deep neural networks end-to-end speech enhancement

来源：评论

学校读者我要写书评

暂无评论

The Temporal Limits Encoder as a sound coding strategy for Bilateral Cochlear Implants

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 265-273页

作者： Kan, Alan Meng, Qinglin Univ Wisconsin Waisman Ctr Madison WI 53705 USA Macquarie Univ Sch Engn N Ryde NSW 2109 Australia South China Univ Technol Sch Phys & Optoelect Acoust Lab Guangzhou 510641 Peoples R China

The difference in binaural benefit between bilateral cochlear implant (CI) users and normal hearing (NH) listeners has typically been attributed to CI sound coding strategies not encoding the acoustic fine structure (FS) interaural time differences (ITD). The Temporal Limits Encoder (TLE) strategy is proposed as a potential way of improving binaural hearing benefits for CI users in noisy situations. TLE works by downward-transposition of midfrequency band-limited channel information and can theoretically provide FS-ITD cues. In thiswork, the effect of choice of lower limit of themodulator in TLE was examined by measuring performance on a word recognition task and computing the magnitude of binaural benefit in bilateral CI users. Performance listening with the TLE strategy was compared with the commonly used Advanced Combinational Encoder (ACE) CI sound coding strategy. Results showed that setting the lower limit to =200 Hz maintained word recognition performance comparable to that of ACE. While most CI listeners exhibited a large binaural benefit (>= 6 dB) in at least one of the conditions tested, there was no systematic relationship between the lower limit of the modulator and performance. These results indicate that the TLE strategy has potential to improve binaural hearing abilities in CI users but further work is needed to understand how binaural benefit can be maximized.

关键词： Assistive technology auditory implant bilateral cochlear implant signal processing sound coding strategy speech processing

来源：评论

学校读者我要写书评

暂无评论

Formant frequency discrimination with a fine structure sound coding strategy for cochlear implants

引用

HEARING RESEARCH 2020年 392卷 107970-107970页

作者： Liepins, R. Kaider, A. Honeder, C. Auinger, A. B. Dahm, V Riss, D. Arnoldner, C. Med Univ Vienna Dept Otolaryngol Head & Neck Surg Vienna Austria Med Univ Vienna Ctr Med Stat Informat & Intelligent Syst Vienna Austria

Recent sound coding strategies for cochlear implants (CI) have focused on the transmission of temporal fine structure to the CI recipient. To date, knowledge about the effects of fine structure coding in electrical hearing is poorly charactarized. The aim of this study was to examine whether the presence of temporal fine structure coding affects how the CI recipient perceives sound. This was done by comparing two sound coding strategies with different temporal fine structure coverage in a longitudinal cross-over setting. The more recent FS4 coding strategy provides fine structure coding on typically four apical stimulation channels compared to FSP with usually one or two fine structure channels. 34 adult CI patients with a minimum CI experience of one year were included. All subjects were fitted according to clinical routine and used both coding strategies for three months in a randomized sequence. Formant frequency discrimination thresholds (FFDT) were measured to assess the ability to resolve timbre information. Further outcome measures included a monosyllables test in quiet and the speech reception threshold of an adaptive matrix sentence test in noise (Oldenburger sentence test). In addition, the subjective sound quality was assessed using visual analogue scales and a sound quality questionnaire after each three months period. The extended fine structure range of FS4 yields FFDT similar to FSP for formants occurring in the frequency range only covered by FS4. There is a significant interaction (p = 0.048) between the extent of fine structure coverage in FSP and the improvement in FFDT in favour of FS4 for these stimuli. FS4 Speech perception in noise and quiet was similar with both coding strategies. sound quality was rated heterogeneously showing that both strategies represent valuable options for CI fitting to allow for best possible individual optimization. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Cochlear implants sound coding strategy Temporal fine structure Formant discrimination Speech perception

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based coding strategy for Improved Cochlear Implant Speech Perception in Noisy Environments

引用

IEEE ACCESS 2025年 13卷 35707-35732页

作者： Essaid, Billel Kheddar, Hamza Batel, Noureddine Chowdhury, Muhammad E. H. Univ MEDEA Elect Engn Dept LSEA Lab Medea 26000 Algeria Qatar Univ Dept Elect Engn Doha Qatar

Automatic speech recognition (ASR) and speech enhancement are essential tools in modern life, aiding not only in machine interaction but also in supporting individuals with hearing impairments. These processes begin with capturing speech in analog form and applying signal processing algorithms to ensure compatibility with devices like cochlear implants (CIs). However, CIs, with their limited number of electrodes, often cause speech distortion, and despite advancements in state-of-the-art signal processing techniques, challenges persist, particularly in noisy environments with multiple speech sources. The rise of artificial intelligence (AI) has introduced innovative strategies to address these limitations. This paper presents a novel deep learning (DL)-based technique that leverages attention mechanisms to improve speech intelligibility through noise suppression. The proposed approach includes two strategies: the first integrates temporal convolutional networks (TCNs) and multi-head attention (MHA) layers to capture both local and global dependencies within the speech signal, enabling precise noise filtering and improved clarity. The second strategy builds on this framework by additionally incorporating bidirectional gated recurrent units (Bi-GRU) alongside TCN and MHA layers, further refining sequence modeling and enhancing noise reduction. The optimal model configuration, using TCN-MHA-Bi-GRU with a kernel size of 16, achieved a compact model size of 788K parameters and recorded training, and validation losses of 0.0350 and 0.0446, respectively. Experimental results on the TIMIT and Harvard Sentences datasets, enriched with diverse noise sources from the DEMAND database, yielded high intelligibility scores with a short-time objective intelligibility (STOI) of 0.8345, word recognition score (WRS) of 99.2636, and an near correlation coefficient (LCC) of 0.9607, underscoring the model's capability to enhance speech perception in noisy CI environments, ensuring a bala

关键词： Speech enhancement Noise measurement Noise reduction Noise Convolutional neural networks Autoencoders Biological system modeling Training Real-time systems Feature extraction Cochlear implant deep learning sound coding strategy speech enhancement transformer

来源：评论

学校读者我要写书评

暂无评论

Speech recognition outcomes in Mandarin-speaking cochlear implant users with fine structure processing

引用

ACTA OTO-LARYNGOLOGICA 2017年第3期137卷 286-292页

作者： Qi, Beier Liu, Ziye Gu, Xin Liu, Bo Capital Med Univ Beijing TongRen Hosp Dept Otolaryngol Head & Neck Surg Beijing Peoples R China Minist Educ Beijing Inst Otolaryngol Key Lab Otolaryngol Head & Neck Surg Beijing Peoples R China Civil Aviat Gen Hosp Beijing Peoples R China

Conclusion: Mandarin-speaking adults can use the Fine Structure Processing (FSP) coding strategy as well as the Continuous Interleaved Sampling (CIS +) coding strategy. No loss in performance was observed after switch-over. Tone identification improves over time with the FSP coding strategy, which is of benefit to tonal-language users. After some time, fine structure was preferred. Objective: This study aimed to determine speech perception, tone perception, and the subjective preferences of Mandarin-speaking adults who received the FSP coding strategy, at upgrade from the CIS +coding strategy. Methods: Thirteen Mandarin-speaking subjects were tested at switch-over from CIS +to the FSP coding strategy similar to 1-month after switch-over, 2-months after switch-over, and 3-months after switch-over with the Mandarin Hearing in Noise Test (M-HINT), the Mandarin Tone Identification in Noise Test (M-TINT), and a visual analogue scale assessing sound and Speech Assessment (SSA). Results: There were no significant differences in the M-HINT between presentation levels (62dB SPL vs 65dB SPL), over time, nor when compared to the CIS +coding strategy. Tone perception improved significantly over time with the FSP coding strategy. Subjects rated the FSP coding strategy with the OPUS 2 as significantly more ' full ' and ' rich ' than with the CIS +coding strategy after 3-months.

关键词： Mandarin cochlear implant fine structure sound coding strategy tone identification

来源：评论

学校读者我要写书评

暂无评论

Perceptual changes with monopolar and phantom electrode stimulation

引用

HEARING RESEARCH 2018年 359卷 64-75页

作者： Klawitter, Silke Landsberger, David M. Buechner, Andreas Nogueira, Waldo Hannover Med Sch Hannover Germany Hannover Med Sch Cluster Excellence Hearing4all Hannover Germany NYU Sch Med New York NY USA

Phantom electrode (PE) stimulation is achieved by simultaneously stimulating out-of-phase from two adjacent intra-cochlear electrodes with different amplitudes. If the basal electrode stimulates with a smaller amplitude than the apical electrode of the pair, the resulting electrical field is pushed away from the basal electrode producing a lower pitch. There is great interest in using PE stimulation in a processing strategy as it can be used to provide stimulation to regions of the cochlea located more apically than the most apical contact on the electrode array. The result is that even lower pitch sensations can be provided without additional risk of a deeper insertion. However, it is unknown if there are perceptual differences between monopolar (MP) and PE stimulation other than a shift in place pitch. Furthermore, it is unknown if the effect and magnitude of changing from MP to PE stimulation is dependent on electrode location. This study investigates the perceptual differences (including pitch and other sound quality differences) at multiple electrode positions using MP and PE stimulation using both a multidimensional scaling procedure (MDS) and a traditional scaling procedure. 10 Advanced Bionics users reported the perceptual distances between 5 single electrode (typically 1, 3, 5, 7, and 9) stimuli in either MP or PE (sigma = 0.5) mode. Subjects were asked to report how perceptually different each pair of stimuli were using any perceived differences except loudness. Subsequently, each stimulus was presented in isolation and subjects scaled how "high" or how "clean" each sounded. Results from the MDS task suggest that perceptual differences between MP and PE stimulation can be explained by a single dimension. The traditional scaling suggests that the single dimension is place pitch. PE stimulation elicits lower pitch perceptions in all cochlear regions. Analysis of Cone Beam Computer Tomography (CBCT) data suggests that PE stimulation may be more effective at t

关键词： Cochlear implant Phantom Multidimensional scaling sound coding strategy

来源：评论

学校读者我要写书评

暂无评论

Stimulation Rate and Voice Pitch Perception in Cochlear Implants

引用

JARO-JOURNAL OF THE ASSOCIATION FOR RESEARCH IN OTOLARYNGOLOGY 2022年第5期23卷 665-680页

作者： Kovacic, Damir James, Chris J. Univ Split Fac Sci Dept Phys Rudera Boskovica 33 Split 21000 Croatia Cochlear France SAS 135 Route St Simon F-31100 Toulouse France

The stimulation rate in cochlear implant (CI) sound coding, or the "carrier" rate in pulses per second (pps), is known to influence pitch perception, as well as loudness perception and sound quality. Our main objective was to investigate the effects of reduced carrier rate on the loudness and pitch of coded speech samples. We describe two experiments with 16 Nucleus (R) CI users, where we controlled modulation characteristics and carrier rate using Spectral and Temporal Enhanced Processing (STEP), a novel experimental multichannel sound coder. We used a fixed set of threshold and comfortable stimulation levels for each subject, obtained from clinical MAPs. In the first experiment, we determined equivalence for voice pitch ranking and voice gender categorization between the Advanced Combination Encoder (ACE), a widely used clinical strategy in Nucleus (R) recipients, and STEP for fundamental frequencies (F0) 120-250 Hz. In the second experiment, loudness was determined as a function of the input amplitude of speech samples for carrier rates of 1000, 500, and 250 pps per channel. Then, using equally loud sound coder programs, we evaluated the effect of carrier rate on voice pitch perception. Although nearly all subjects could categorize voice gender significantly above chance, pitch ranking varied across subjects. Overall, carrier rate did not substantially affect voice pitch ranking or voice gender categorization: as long as the carrier rate was at least twice the fundamental frequency, or when stimulation pulses for the lowest, 250 pps carrier were aligned to F0 peaks. These results indicate that carrier rates as low as 250 pps per channel are sufficient to support functional voice pitch perception for those CI users sensitive to temporal pitch cues;at least when temporal modulations and pulse timings in the coder output are well controlled by novel strategies such as STEP.

关键词： cochlear implants sound coding strategy stimulation rate loudness voice pitch voice gender categorization

来源：评论

学校读者我要写书评

暂无评论

AN END-TO-END DEEP LEARNING SPEECH coding AND DENOISING strategy FOR COCHLEAR IMPLANTS 47

AN END-TO-END DEEP LEARNING SPEECH CODING AND DENOISING STRA...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Gajecki, Tom Nogueira, Waldo Hannover Med Sch Dept Otolaryngol D-30625 Hannover Germany Cluster Excellence Hearing4all D-30625 Hannover Germany

ISBN: (纸本)9781665405409

Cochlear implant (CI) users struggle to understand speech in noisy conditions. To address this problem, we propose a deep learning speech denoising sound coding strategy that estimates the CI electric stimulation patterns out of the raw audio data captured by the microphone, performing end-to-end CI processing. To estimate the relative denoising performance differences between various approaches, we compared this technique to a classic Wiener filter and to a conv-TasNet. Speech enhancement performance was assessed by means of signal-to-noise-ratio improvement and the short-time objective speech intelligibility measure. Additionally, 5 CI users were evaluated for speech intelligibility in noise to assess the potential benefits of each algorithm. Our results show that the proposed method is capable of replacing a CI sound coding strategy while preserving its general use for every listener and performing speech enhancement in noisy environments, without sacrificing algorithmic latency.

关键词： Cochlear Implant Deep Learning sound coding strategy Speech Enhancement

来源：评论

学校读者我要写书评

暂无评论

Optimization of sound coding Strategies to Make Singing Music More Accessible for Cochlear Implant Users

引用

TRENDS IN HEARING 2023年 27卷 23312165221148022-23312165221148022页

作者： Tahmasebi, Sina Segovia-Martinez, Manuel Nogueira, Waldo Hannover Med Sch Dept Otolaryngol Hannover Germany Cluster Excellence Hearing4all Hannover Germany Oticon Med Vallauris France Karl Wiechert Allee 3 D-30625 Hannover Germany

Cochlear implants (CIs) are implantable medical devices that can partially restore hearing to people suffering from profound sensorineural hearing loss. While these devices provide good speech understanding in quiet, many CI users face difficulties when listening to music. Reasons include poor spatial specificity of electric stimulation, limited transmission of spectral and temporal fine structure of acoustic signals, and restrictions in the dynamic range that can be conveyed via electric stimulation of the auditory nerve. The coding strategies currently used in CIs are typically designed for speech rather than music. This work investigates the optimization of CI coding strategies to make singing music more accessible to CI users. The aim is to reduce the spectral complexity of music by selecting fewer bands for stimulation, attenuating the background instruments by strengthening a noise reduction algorithm, and optimizing the electric dynamic range through a back-end compressor. The optimizations were evaluated through both objective and perceptual measures of speech understanding and melody identification of singing voice with and without background instruments, as well as music appreciation questionnaires. Consistent with the objective measures, results gathered from the perceptual evaluations indicated that reducing the number of selected bands and optimizing the electric dynamic range significantly improved speech understanding in music. Moreover, results obtained from questionnaires show that the new music back-end compressor significantly improved music enjoyment. These results have potential as a new CI program for improved singing music perception.

关键词： cochlear implant music perception sound coding strategy dynamic range compression

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：