A Sparse Conjugate Gradient Adaptive Filter.

In this letter, we propose a novel conjugate gradient (CG) adaptive filtering algorithm for online estimation of system responses that admit sparsity. Specifically, the Sparsity-promoting Conjugate Gradient (SCG) algorithm is developed based on iterative reweighting methods popular in the sparse signal recovery area. We propose an affine scaling transformation strategy within the reweighting framework, leading to an algorithm that allows the usage of a zero sparsity regularization coefficient. This enables SCG to leverage the sparsity of the system response if it already exists, while not compromising the optimization process. Simulation results show that SCG demonstrates improved convergence and steady-state properties over existing methods.

A unified framework for sparse non-negative least squares using multiplicative updates and the non-negative matrix factorization problem.

We study the sparse non-negative least squares (S-NNLS) problem. S-NNLS occurs naturally in a wide variety of applications where an unknown, non-negative quantity must be recovered from linear measurements. We present a unified framework for S-NNLS based on a rectified power exponential scale mixture prior on the sparse codes. We show that the proposed framework encompasses a large class of S-NNLS algorithms and provide a computationally efficient inference procedure based on multiplicative update rules. Such update rules are convenient for solving large sets of S-NNLS problems simultaneously, which is required in contexts like sparse non-negative matrix factorization (S-NMF). We provide theoretical justification for the proposed approach by showing that the local minima of the objective function being optimized are sparse and the S-NNLS algorithms presented are guaranteed to converge to a set of stationary points of the objective function. We then extend our framework to S-NMF, showing that our framework leads to many well known S-NMF algorithms under specific choices of prior and providing a guarantee that a popular subclass of the proposed algorithms converges to a set of stationary points of the objective function. Finally, we study the performance of the proposed approaches on synthetic and real-world data.

Speech quality and stable gain trade-offs in adaptive feedback cancellation for hearing aids.

This paper addresses trade-offs in adaptive feedback cancellation (AFC) for hearing aids. Aggressive AFC for improved added stable gain (ASG) reduces speech quality. In this paper, the hearing-aid speech quality index (HASQI) is used to investigate AFC performance before the system becomes unstable. It is demonstrated that for a desired speech quality, multiple AFC algorithms can be evaluated for their ASG and computational efficiency. An example is presented with HASQI = 0.8, baseline AFC, and two advanced approaches. For the advanced AFCs, ASG gains of 4 and 7 dB were obtained at additional computational complexity of 8% and 11%, respectively.

Real-Time Multirate Multiband Amplification for Hearing Aids.

Hearing loss is a common problem affecting the quality of life for thousands of people. However, many individuals with hearing loss are dissatisfied with the quality of modern hearing aids. Amplification is the main method of compensating for hearing loss in modern hearing aids. One common amplification technique is dynamic range compression, which maps audio signals onto a person's hearing range using an amplification curve. However, due to the frequency dependent nature of the human cochlea, compression is often performed independently in different frequency bands. This paper presents a real-time multirate multiband amplification system for hearing aids, which includes a multirate channelizer for separating an audio signal into eleven standard audiometric frequency bands, and an automatic gain control system for accurate control of the steady state and dynamic behavior of audio compression as specified by ANSI standards. The spectral channelizer offers high frequency resolution with low latency of 5.4 ms and about 14× improvement in complexity over a baseline design. Our automatic gain control includes a closed-form solution for satisfying any designated attack and release times for any desired compression parameters. The increased frequency resolution and precise gain adjustment allow our system to more accurately fulfill audiometric hearing aid prescriptions.

Multimodal assessment of spasticity using a point-of-care instrumented glove to separate neural and biomechanical contributions.

Accurate assessment of spasticity is crucial for physicians to select the most suitable treatment for patients. However, the current clinical practice standard is limited by imprecise assessment scales relying on perception. Here, we equipped the clinician with a portable, multimodal sensor glove to shift bedside evaluations from subjective perception to objective measurements. The measurements were correlated with biomechanical properties of muscles and revealed dynamic characteristics of spasticity, including catch symptoms and velocity-dependent resistance. Using the biomechanical data, a radar metric was developed for ranking severity in spastic knees and elbows. The continuous monitoring results during anesthesia induction enable the separation of neural and structural contributions to spasticity in 21 patients. This work delineated effects of reflex excitations from structural abnormalities, to classify underlying causes of spasticity that will inform treatment decisions for evidence-based patient care.

Proportionate Adaptive Filtering Algorithms Derived Using an Iterative Reweighting Framework.

In this paper, based on sparsity-promoting regularization techniques from the sparse signal recovery (SSR) area, least mean square (LMS)-type sparse adaptive filtering algorithms are derived. The approach mimics the iterative reweighted ℓ 2 and ℓ 1 SSR methods that majorize the regularized objective function during the optimization process. We show that introducing the majorizers leads to the same algorithm as simply using the gradient update of the regularized objective function, as is done in existing approaches. Different from the past works, the reweighting formulation naturally leads to an affine scaling transformation (AST) strategy, which effectively introduces a diagonal weighting on the gradient, giving rise to new algorithms that demonstrate improved convergence properties. Interestingly, setting the regularization coefficient to zero in the proposed AST-based framework leads to the Sparsity-promoting LMS (SLMS) and Sparsity-promoting Normalized LMS (SNLMS) algorithms, which exploit but do not strictly enforce the sparsity of the system response if it already exists. The SLMS and SNLMS realize proportionate adaptation for convergence speedup should sparsity be present in the underlying system response. In this manner, we develop a new way for rigorously deriving a large class of proportionate algorithms, and also explain why they are useful in applications where the underlying systems admit certain sparsity, e.g., in acoustic echo and feedback cancellation.

ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees.

Models recently used in the literature proving residual networks (ResNets) are better than linear predictors are actually different from standard ResNets that have been widely used in computer vision. In addition to the assumptions such as scalar-valued output or single residual block, the models fundamentally considered in the literature have no nonlinearities at the final residual representation that feeds into the final affine layer. To codify such a difference in nonlinearities and reveal a linear estimation property, we define ResNEsts, i.e., Residual Nonlinear Estimators, by simply dropping nonlinearities at the last residual representation from standard ResNets. We show that wide ResNEsts with bottleneck blocks can always guarantee a very desirable training property that standard ResNets aim to achieve, i.e., adding more blocks does not decrease performance given the same set of basis elements. To prove that, we first recognize ResNEsts are basis function models that are limited by a coupling problem in basis learning and linear prediction. Then, to decouple prediction weights from basis learning, we construct a special architecture termed augmented ResNEst (A-ResNEst) that always guarantees no worse performance with the addition of a block. As a result, such an A-ResNEst establishes empirical risk lower bounds for a ResNEst using corresponding bases. Our results demonstrate ResNEsts indeed have a problem of diminishing feature reuse; however, it can be avoided by sufficiently expanding or widening the input space, leading to the above-mentioned desirable property. Inspired by the densely connected networks (DenseNets) that have been shown to outperform ResNets, we also propose a corresponding new model called Densely connected Nonlinear Estimator (DenseNEst). We show that any DenseNEst can be represented as a wide ResNEst with bottleneck blocks. Unlike ResNEsts, DenseNEsts exhibit the desirable property without any special architectural re-design.

Multirate Audiometric Filter Bank for Hearing Aid Devices.

The frequency-dependent nature of hearing loss poses many challenges for hearing aid design. In order to compensate for a hearing aid user's unique hearing loss pattern, an input signal often needs to be separated into frequency bands, or channels, through a process called sub-band decomposition. In this paper, we present a real-time filter bank for hearing aids. Our filter bank features 10 channels uniformly distributed on the logarithmic scale, located at the standard audiometric frequencies used for the characterization and fitting of hearing aids. We obtained filters with very narrow passbands in the lower frequencies by employing multi-rate signal processing. Our filter bank offers a 9.1× reduction in complexity as compared to conventional signal processing. We implemented our filter bank on Open Speech Platform, an open-source hearing aid, and confirmed real-time operation.

Unsupervised Sequence Alignment between Video and Human Center of Pressure.

Center of pressure (COP) estimation with images/videos as input achieves accurate precision with the development of the human skeleton joint extraction tasks. As a supervised learning task, correct labels acquired from COP with regard to the input images/videos are significant. Thus, synchronization between these two different types of sequences is necessary. If these two different modalities are misaligned, the downstream tasks' precision is affected significantly due to the inaccurate labels from the COP sequence. In this paper, we used a synchronized dataset and unsupervised deep learning to train an Alignment Network to align video and COP sequences on another unsynchronized dataset where each sequence starts at a different time and has different frame rates. On the synchronized dataset, the Alignment Network removes 84.4% of temporal offset. On the unsynchronized dataset, we proposed a simple yet effective Differential Network to simulate one practical downstream task. We used the differential Network to estimate the sway level of COP. Results show that this method achieved significant improvement (over 20% improvement on three sway level cases) over the misaligned dataset.

Hearing Aid Self-Adjustment: Effects of Formal Speech-Perception Test and Noise.

While listening to recorded sentences with a sound-field level of 65 dB SPL, 24 adults with hearing-aid experience used the "Goldilocks" explore-and-select procedure to adjust level and spectrum of amplified speech to preference. All participants started adjustment from the same generic response. Amplification was provided by a custom-built Master Hearing Aid with online processing of microphone input. Primary goals were to assess the effects of including a formal speech-perception test between repeated self-adjustments and of adding multitalker babble (signal-to-noise ratio +6 dB) during self-adjustment. The speech test did not affect group-mean self-adjusted output, which was close to the National Acoustics Laboratories' prescription for Non-Linear hearing aids. Individuals, however, showed a wide range of deviations from this prescription. Extreme deviations at the first self-adjustment fell by a small but significant amount at the second. The multitalker babble had negligible effect on group-mean self-selected output but did have predictable effects on word recognition in sentences and on participants' opinion regarding the most important subjective criterion guiding self-adjustment. Phoneme recognition in monosyllabic words was better with the generic starting response than without amplification and improved further after self-adjustment. The findings continue to support the efficacy of hearing aid self-fitting, at least for level and spectrum. They do not support the need for inclusion of a formal speech-perception test, but they do support the value of completing more than one self-adjustment. Group-mean data did not indicate a need for threshold-based prescription as a starting point for self-adjustment.

SSGD: SPARSITY-PROMOTING STOCHASTIC GRADIENT DESCENT ALGORITHM FOR UNBIASED DNN PRUNING.

While deep neural networks (DNNs) have achieved state-of-the-art results in many fields, they are typically over-parameterized. Parameter redundancy, in turn, leads to inefficiency. Sparse signal recovery (SSR) techniques, on the other hand, find compact solutions to overcomplete linear problems. Therefore, a logical step is to draw the connection between SSR and DNNs. In this paper, we explore the application of iterative reweighting methods popular in SSR to learning efficient DNNs. By efficient, we mean sparse networks that require less computation and storage than the original, dense network. We propose a reweighting framework to learn sparse connections within a given architecture without biasing the optimization process, by utilizing the affine scaling transformation strategy. The resulting algorithm, referred to as Sparsity-promoting Stochastic Gradient Descent (SSGD), has simple gradient-based updates which can be easily implemented in existing deep learning libraries. We demonstrate the sparsification ability of SSGD on image classification tasks and show that it outperforms existing methods on the MNIST and CIFAR-10 datasets.

Jointly Leveraging Decorrelation and Sparsity for Improved Feedback Cancellation in Hearing Aids.

We propose a new adaptive feedback cancellation (AFC) system in hearing aids (HAs) based on a well-posed optimization criterion that jointly considers both decorrelation of the signals and sparsity of the underlying channel. We show that the least squares criterion on subband errors regularized by a p-norm-like diversity measure can be used to simultaneously decorrelate the speech signals and exploit sparsity of the acoustic feedback path impulse response. Compared with traditional subband adaptive filters that are not appropriate for incorporating sparsity due to shorter sub-filters, our proposed framework is suitable for promoting sparse characteristics, as the update rule utilizing subband information actually operates in the fullband. Simulation results show that the normalized misalignment, added stable gain, and other objective metrics of the AFC are significantly improved by choosing a proper sparsity promoting factor and a suitable number of subbands. More importantly, the results indicate that the benefits of subband decomposition and sparsity promoting are complementary and additive for AFC in HAs.

Common Configurations of Real-Ear Aided Response Targets Prescribed by NAL-NL2 for Older Adults With Mild-to-Moderate Hearing Loss.

Purpose This study investigates common real-ear aided response (REAR) configurations prescribed by the NAL-NL2 algorithm for older adults with hearing loss. Method A data set that is representative of the older adult U.S. population with mild-to-moderate sensorineural hearing loss was constructed from the audiometric data of 934 adults (aged 55-85 years) from the National Health and Nutrition Examination Survey years 1999-2012. Two clustering approaches were implemented to generate common REAR configurations for eight frequencies (0.25, 0.5, 1, 2, 3, 4, 6, and 8 kHz) at three input levels (55, 65, and 75 dB SPL). (a) In the REAR-based clustering approach, the National Health and Nutrition Examination Survey audiograms were first converted to REAR targets and then clustered to generate common REAR configurations. (b) In the audiogram-based clustering approach, the audiograms were first clustered into common hearing loss profiles and then converted to REAR configurations. The trade-off between the number of available REAR configurations and the percentage of the U.S. population whose hearing loss could be fit by at least one of them (i.e., percent coverage) was evaluated. Hearing loss fit was defined as less than ± 5-dB difference between an individual's REAR targets and those of the clustered REAR configuration. Results Percent coverage increases with the number of available REAR configurations, with four configurations resulting in 75% population coverage. Overall, REAR-based clustering yielded 5 percentage points better coverage on average compared to audiogram-based clustering. Conclusions The common REAR configurations can be used for programming the gain frequency responses in preconfigured over-the-counter hearing aids and provide clinically appropriate amplification settings for older adults with mild-to-moderate hearing loss.

Open Speech Platform: Democratizing Hearing Aid Research.

Hearing aids help overcome the challenges associated with hearing loss, and thus greatly benefit and improve the lives of those living with hearing-impairment. Unfortunately, there is a lack of adoption of hearing aids among those that can benefit from hearing aids. Hearing researchers and audiologists are trying to address this problem through their research. However, the current proprietary hearing aid market makes it difficult for academic researchers to translate their findings into commercial use. In order to abridge this gap and accelerate research in hearing health care, we present the design and implementation of the Open Speech Platform (OSP), which consists of a co-design of open-source hardware and software. The hardware meets the industry standards and enables researchers to conduct experiments in the field. The software is designed with a systematic and modular approach to standardize algorithm implementation and simplify user interface development. We evaluate the performance of OSP regarding both its hardware and software, as well as demonstrate its usefulness via a self-fitting study involving human participants.

Proportionate Adaptive Filters Based on Minimizing Diversity Measures for Promoting Sparsity.

In this paper, a novel way of deriving proportionate adaptive filters is proposed based on diversity measure minimization using the iterative reweighting techniques well-known in the sparse signal recovery (SSR) area. The resulting least mean square (LMS)-type and normalized LMS (NLMS)-type sparse adaptive filtering algorithms can incorporate various diversity measures that have proved effective in SSR. Furthermore, by setting the regularization coefficient of the diversity measure term to zero in the resulting algorithms, Sparsity promoting LMS (SLMS) and Sparsity promoting NLMS (SNLMS) are introduced, which exploit but do not strictly enforce the sparsity of the system response if it already exists. Moreover, unlike most existing proportionate algorithms that design the step-size control factors based on heuristics, our SSR-based framework leads to designing the factors in a more systematic way. Simulation results are presented to demonstrate the convergence behavior of the derived algorithms for systems with different sparsity levels.

On Mitigating Acoustic Feedback in Hearing Aids with Frequency Warping by All-Pass Networks.

Acoustic feedback control continues to be a challenging problem due to the emerging form factors in advanced hearing aids (HAs) and hearables. In this paper, we present a novel use of well-known all-pass filters in a network to perform frequency warping that we call "freping." Freping helps in breaking the Nyquist stability criterion and improves adaptive feedback cancellation (AFC). Based on informal subjective assessments, distortions due to freping are fairly benign. While common objective metrics like the perceptual evaluation of speech quality (PESQ) and the hearing-aid speech quality index (HASQI) may not adequately capture distortions due to freping and acoustic feedback artifacts from a perceptual perspective, they are still instructive in assessing the proposed method. We demonstrate quality improvements with freping for a basic AFC (PESQ: 2.56 to 3.52 and HASQI: 0.65 to 0.78) at a gain setting of 20; and an advanced AFC (PESQ: 2.75 to 3.17 and HASQI: 0.66 to 0.73) for a gain of 30. From our investigations, freping provides larger improvement for basic AFC, but still improves overall system performance for many AFC approaches.

A Generalized Proportionate-Type Normalized Subband Adaptive Filter.

We show that a new design criterion, i.e., the least squares on subband errors regularized by a weighted norm, can be used to generalize the proportionate-type normalized subband adaptive filtering (PtNSAF) framework. The new criterion directly penalizes subband errors and includes a sparsity penalty term which is minimized using the damped regularized Newton's method. The impact of the proposed generalized PtNSAF (GPtNSAF) is studied for the system identification problem via computer simulations. Specifically, we study the effects of using different numbers of subbands and various sparsity penalty terms for quasi-sparse, sparse, and dispersive systems. The results show that the benefit of increasing the number of subbands is larger than promoting sparsity of the estimated filter coefficients when the target system is quasi-sparse or dispersive. On the other hand, for sparse target systems, promoting sparsity becomes more important. More importantly, the two aspects provide complementary and additive benefits to the GPtNSAF for speeding up convergence.

Robust Biopotential Acquisition via a Distributed Multi-Channel FM-ADC.

This contribution presents an active electrode system for biopotential acquisition using a distributed multi-channel FM-modulated analog front-end and ADC architecture. Each electrode captures one biopotential signal and converts to a frequency modulated signal using a VCO tuned to a unique frequency. Each electrode then buffers its output onto a shared analog line that aggregates all of the FM-modulated channels. This aggregation results in rugged, wearable form factor by eliminating wire clutter of traditional systems. A gateway integrated circuit then digitizes the composite FM signal and transmits for further processing. The coding gain due to bandwidth expansion of FM provides a large usable dynamic range (DR) and the single ADC for multiple channels results in significant power savings. Finally, the use of FM signals between the transducers and ADC provides resilience to motion and EMI artifacts. The system is implemented in 65 nm silicon using two distinct 1 mm 2 chip designs. Six-channel operation is demonstrated using FM channels with center frequencies around 15 MHz and the system achieves a usable DR of over 100 dB, while achieving figure of merit competitive with state of the art prior works using traditional approaches.

A Wearable, Extensible, Open-Source Platform for Hearing Healthcare Research.

Hearing loss is one of the most common conditions affecting older adults worldwide. Frequent complaints from the users of modern hearing aids include poor speech intelligibility in noisy environments and high cost, among other issues. However, the signal processing and audiological research needed to address these problems has long been hampered by proprietary development systems, underpowered embedded processors, and the difficulty of performing tests in real-world acoustical environments. To facilitate existing research in hearing healthcare and enable new investigations beyond what is currently possible, we have developed a modern, open-source hearing research platform, Open Speech Platform (OSP). This paper presents the system design of the complete OSP wearable platform, from hardware through firmware and software to user applications. The platform provides a complete suite of basic and advanced hearing aid features which can be adapted by researchers. It serves web apps directly from a hotspot on the wearable hardware, enabling users and researchers to control the system in real time. In addition, it can simultaneously acquire high-quality electroencephalography (EEG) or other electrophysiological signals closely synchronized to the audio. All of these features are provided in a wearable form factor with enough battery life for hours of operation in the field.

Bone-Conduction Sensor Assisted Noise Estimation for Improved Speech Enhancement.

State-of-the-art noise power spectral density (PSD) estimation techniques for speech enhancement utilize the so-called speech presence probability (SPP). However, in highly non-stationary environments, SPP-based techniques could still suffer from inaccurate estimation, leading to significant amount of residual noise or speech distortion. In this paper, we propose to improve speech enhancement by deploying the bone-conduction (BC) sensor, which is known to be relatively insensitive to the environmental noise compared to the regular air-conduction (AC) microphone. A strategy is suggested to utilized the BC sensor characteristics for assisting the AC microphone in better SPP-based noise estimation. To our knowledge, no previous work has incorporated the BC sensor in this noise estimation aspect. Consequently, the proposed strategy can possibly be combined with other BC sensor assisted speech enhancement techniques. We show the feasibility and potential of the proposed method for improving the enhanced speech quality by both objective and subjective tests.