Ying-Hui Lai

Micro-Raman for diamond film stress analysis

Abstract The residual stress in microwave plasma-enhanced CVD diamond film was analyzed using a Raman spectrometer with micrometer spatial resolution. This enables effective study of isolated crystals grown in the same deposition run. A variation of the Raman line shape near 1332 cm −1 was observed from different crystals in the same sample. A phenomenological model was used to describe the shift and splitting of the diamond Raman line, from which the type and the magnitude of the stress in PECVD grown diamond can be assessed. The interrelationship and the origin of the stress in the film is discussed.

Generalized maximum a posteriori spectral amplitude estimation for speech enhancement

GMAPA specifies the weight of prior density based on the SNR of the testing speech signals.GMAPA is capable of performing environment-aware speech enhancement.When the SNR is high, GMAPA adopts a small weight to prevent overcompensations.When the SNR is low, GMAPA uses a large weight to avoid disturbance of the restoration.Results show that GMAPA outperforms related approaches in objective and subjective evaluations. Spectral restoration methods for speech enhancement aim to remove noise components in noisy speech signals by using a gain function in the spectral domain. How to design the gain function is one of the most important parts for obtaining enhanced speech with good quality. In most studies, the gain function is designed by optimizing a criterion based on some assumptions of the noise and speech distributions, such as minimum mean square error (MMSE), maximum likelihood (ML), and maximum a posteriori (MAP) criteria. The MAP criterion shows advantage in obtaining a more reliable gain function by incorporating a suitable prior density. However, it has a problem as several studies showed: although MAP based estimator effectively reduces noise components when the signal-to-noise ratio (SNR) is low, it brings large speech distortion when the SNR is high. For solving this problem, we have proposed a generalized maximum a posteriori spectral amplitude (GMAPA) algorithm in designing a gain function for speech enhancement. The proposed GMAPA algorithm dynamically specifies the weight of prior density of speech spectra according to the SNR of the testing speech signals to calculate the optimal gain function. When the SNR is high, GMAPA adopts a small weight to prevent overcompensations that may result in speech distortions. On the other hand, when the SNR is low, GMAPA uses a large weight to avoid disturbance of the restoration caused by measurement noises. In our previous study, it has been proven that the weight of the prior density plays a crucial role to the GMAPA performance, and the weight is determined based on the SNR in an utterance-level. In this paper, we propose to compute the weight with the consideration of time-frequency correlations that result in a more accurate estimation of the gain function. Experiments were carried out to evaluate the proposed algorithm on both objective tests and subjective tests. The experimental results obtained from objective tests indicate that GMAPA is promising compared to several well-known algorithms at both high and low SNRs. The results of subjective listening tests indicate that GMAPA provides significantly higher sound quality than other speech enhancement algorithms.

Measuring the long-term SNRs of static and adaptive compression amplification techniques for speech in noise.

BACKGROUND Multichannel wide-dynamic-range compression (WDRC) is a widely adopted amplification scheme in modern digital hearing aids. It attempts to provide individuals with loudness recruitment with superior speech intelligibility and greater listening comfort over a wider range of input levels. However, recent surveys have shown that compression processing (operating in the nonlinear regime) usually reduces the long-term signal-to-noise ratio (SNR). PURPOSE The purpose of this study was to determine the long-term SNR in an adaptive compression-ratio (CR) amplification scheme called adaptive wide-dynamic-range compression (AWDRC), and to determine whether this concept is better than static WDRC amplification at improving the long-term SNR for speech in noise. DESIGN AND STUDY SAMPLE AWDRC uses the input short-term dynamic range to adjust the CR to maximize audibility and comfort. Various methods for evaluating the long-term SNR were used to observe the relationship between the CR and output SNR performance in AWDRC for seven typical audiograms, and to compare the results with those for static WDRC amplification. RESULTS The results showed that the variation of the CR in AWDRC amplification can maintain the comfort and audibility of the output sound. In addition, the average long-term SNR improved by 0.1-5.5 dB for a flat hearing loss, by 0.2-3.4 dB for a reverse sloping hearing loss, by 1.4-4.8 dB for a high-frequency hearing loss, and by 0.3-5.7 dB for a mild-to-moderate-sloping high-frequency hearing loss relative to static WDRC amplification. The output long-term SNR differed significantly (p < .001) between static WDRC and AWDRC amplification. CONCLUSIONS The results of this study show that AWDRC, which uses the characteristics of the input signal to adaptively adjust the CR, provides better long-term SNR performance than static WDRC amplification.

S1 and S2 Heart Sound Recognition Using Deep Neural Networks

OBJECTIVE This study focuses on the first (S1) and second (S2) heart sound recognition based only on acoustic characteristics; the assumptions of the individual durations of S1 and S2 and time intervals of S1-S2 and S2-S1 are not involved in the recognition process. The main objective is to investigate whether reliable S1 and S2 recognition performance can still be attained under situations where the duration and interval information might not be accessible. METHODS A deep neural network (DNN) method is proposed for recognizing S1 and S2 heart sounds. In the proposed method, heart sound signals are first converted into a sequence of Mel-frequency cepstral coefficients (MFCCs). The K-means algorithm is applied to cluster MFCC features into two groups to refine their representation and discriminative capability. The refined features are then fed to a DNN classifier to perform S1 and S2 recognition. We conducted experiments using actual heart sound signals recorded using an electronic stethoscope. Precision, recall, F-measure, and accuracy are used as the evaluation metrics. RESULTS The proposed DNN-based method can achieve high precision, recall, and F-measure scores with more than 91% accuracy rate. CONCLUSION The DNN classifier provides higher evaluation scores compared with other well-known pattern classification methods. SIGNIFICANCE The proposed DNN-based method can achieve reliable S1 and S2 recognition performance based on acoustic characteristics without using an ECG reference or incorporating the assumptions of the individual durations of S1 and S2 and time intervals of S1-S2 and S2-S1.

A Study of Adaptive WDRC in Hearing Aids under Noisy Conditions

Background noise poses a great challenge to the speech recognition capability of hearing-impaired patients fitted with hearing aid (HA) devices. In an HA system, a speech enhancement unit is generally employed to enhance the signal-to-noise ratio (SNR) of noisy speech in order to yield better speech understanding for HA users in noisy conditions. However, previous studies reported that a subsequent static amplification scheme, such as wide-dynamic- range compression (WDRC), may deteriorate the enhanced speech and thus decrease the speech recognition capability. This work examines the performance of a recently proposed adaptive WDRC (AWDRC) amplification scheme when used in conjunction with a speech enhancement method in HA signal processing. Experimental results demonstrate that when integrated with the same speech enhancement method, AWDRC outperforms WDRC, in terms of long-term SNRs, at several typical hearing loss conditions. The results suggest that AWDRC can be a better choice than WDRC when combining with speech enhancement to improve speech recognition capabilities for HA users in noisy conditions.

A Deep Denoising Autoencoder Approach to Improving the Intelligibility of Vocoded Speech in Cochlear Implant Simulation

Objective: In a cochlear implant (CI) speech processor, noise reduction (NR) is a critical component for enabling CI users to attain improved speech perception under noisy conditions. Identifying an effective NR approach has long been a key topic in CI research. Method: Recently, a deep denoising autoencoder (DDAE) based NR approach was proposed and shown to be effective in restoring clean speech from noisy observations. It was also shown that DDAE could provide better performance than several existing NR methods in standardized objective evaluations. Following this success with normal speech, this paper further investigated the performance of DDAE-based NR to improve the intelligibility of envelope-based vocoded speech, which simulates speech signal processing in existing CI devices. Results: We compared the performance of speech intelligibility between DDAE-based NR and conventional single-microphone NR approaches using the noise vocoder simulation. The results of both objective evaluations and listening test showed that, under the conditions of nonstationary noise distortion, DDAE-based NR yielded higher intelligibility scores than conventional NR approaches. Conclusion and significance: This study confirmed that DDAE-based NR could potentially be integrated into a CI processor to provide more benefits to CI users under noisy conditions.

Improving denoising auto-encoder based speech enhancement with the speech parameter generation algorithm

This paper investigates the use of the speech parameter generation (SPG) algorithm, which has been successfully adopted in deep neural network (DNN)-based voice conversion (VC) and speech synthesis (SS), for incorporating temporal information to improve the deep denoising auto-encoder (DDAE)-based speech enhancement. In our previous studies, we have confirmed that DDAE could effectively suppress noise components from noise corrupted speech. However, because DDAE converts speech in a frame by frame manner, the enhanced speech shows some level of discontinuity even though context features are used as input to the DDAE. To handle this issue, this study proposes using the SPG algorithm as a post-processor to transform the DDAE processed feature sequence to one with a smoothed trajectory. Two types of temporal information with SPG are investigated in this study: static-dynamic and context features. Experimental results show that the SPG with context features outperforms the SPG with static-dynamic features and the baseline system, which considers context features without SPG, in terms of standardized objective tests in different noise types and SNRs.

Effects of Adaptation Rate and Noise Suppression on the Intelligibility of Compressed-Envelope Based Speech.

Temporal envelope is the primary acoustic cue used in most cochlear implant (CI) speech processors to elicit speech perception for patients fitted with CI devices. Envelope compression narrows down envelope dynamic range and accordingly degrades speech understanding abilities of CI users, especially under challenging listening conditions (e.g., in noise). A new adaptive envelope compression (AEC) strategy was proposed recently, which in contrast to the traditional static envelope compression, is effective at enhancing the modulation depth of envelope waveform by making best use of its dynamic range and thus improving the intelligibility of envelope-based speech. The present study further explored the effect of adaptation rate in envelope compression on the intelligibility of compressed-envelope based speech. Moreover, since noise reduction is another essential unit in modern CI systems, the compatibility of AEC and noise reduction was also investigated. In this study, listening experiments were carried out by presenting vocoded sentences to normal hearing listeners for recognition. Experimental results demonstrated that the adaptation rate in envelope compression had a notable effect on the speech intelligibility performance of the AEC strategy. By specifying a suitable adaptation rate, speech intelligibility could be enhanced significantly in noise compared to when using static envelope compression. Moreover, results confirmed that the AEC strategy was suitable for combining with noise reduction to improve the intelligibility of envelope-based speech in noise.

Development and Preliminary Verification of a Mandarin-Based Hearing-Aid Fitting Strategy

Objective The purpose of this study was to design and to verify a new hearing-aid fitting strategy (Aescu HRL-1) based on the acoustic features of Mandarin. The subjective and objective outcomes were compared to those fitted with NAL-NL1 (National Acoustic Laboratory Non-Linear, version1) in Mandarin-speaking hearing-aid users. Design Fifteen subjects with sensorineural hearing loss participated in this preliminary study. Each subject wore a pair of four-channel hearing aids fitted with the Aescu HRL-1 and NAL-NL1 prescriptions alternatively for 1 month. Objective and subjective tests including the Mandarin Monosyllable Recognition Test (MMRT), Mandarin Hearing in Noise Test (MHINT), International Outcome Inventory for Hearing Aids (IOI-HA), and a sound-quality questionnaire were used to evaluate the performance of the two prescriptions. Results The mean MMRT scores were 79.9% and 81.1% for NAL-NL1 and Aescu HRL-1 respectively. They are not statistically different. The corresponding MHINT signal-to-noise ratios were 0.87 and 0.85 dB, also, no significant difference was found between these two strategies. However, in subjective questionnaires, overall, the sound-quality and IOI-HA scores were higher for Aescu HRL-1. Conclusions The speech recognition performance based on Aescu HRL-1 is as good as that of NAL-NL1 for Mandarin-speaking hearing-aid users. Moreover, the subjects generally responded that Aescu HRL-1 provides a more natural, richer, and better sound quality than does NAL-NL1.

Evaluation of generalized maximum a posteriori spectral amplitude (GMAPA) speech enhancement algorithm in hearing aids

Speech enhancement is an important segment in digital hearing aids, which aims to improve signal-to-noise (SNR) level of received speech signals and thus enhance speech intelligibility for hearing-loss individuals. Recently, we proposed a generalized maximum a posteriori spectral amplitude (GMAPA) speech enhancement algorithm. The proposed GMAPA algorithm has been confirmed effective in a series of objective evaluations and speech recognition tests. In this study, we conduct experiments and observe that GMAPA also provides clear long-term SNR increases in a simulated hearing-aids testing condition. The result demonstrates that GMAPA can be suitably applied in digital hearing aids.