Improving the Intelligibility of Speech for Simulated Electric and Acoustic Stimulation Using Fully Convolutional Neural Networks.

Combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under quiet conditions. However, when noise signals are involved, both the electric signal and the acoustic signal may be distorted, thereby resulting in poor recognition performance. To suppress noise effects, speech enhancement (SE) is a necessary unit in EAS devices. Recently, a time-domain speech enhancement algorithm based on the fully convolutional neural networks (FCN) with a short-time objective intelligibility (STOI)-based objective function (termed FCN(S) in short) has received increasing attention due to its simple structure and effectiveness of restoring clean speech signals from noisy counterparts. With evidence showing the benefits of FCN(S) for normal speech, this study sets out to assess its ability to improve the intelligibility of EAS simulated speech. Objective evaluations and listening tests were conducted to examine the performance of FCN(S) in improving the speech intelligibility of normal and vocoded speech in noisy environments. The experimental results show that, compared with the traditional minimum-mean square-error SE method and the deep denoising autoencoder SE method, FCN(S) can obtain better gain in the speech intelligibility for normal as well as vocoded speech. This study, being the first to evaluate deep learning SE approaches for EAS, confirms that FCN(S) is an effective SE approach that may potentially be integrated into an EAS processor to benefit users in noisy environments.

Joint Dictionary Learning-Based Non-Negative Matrix Factorization for Voice Conversion to Improve Speech Intelligibility After Oral Surgery.

Objective: This paper focuses on machine learning based voice conversion (VC) techniques for improving the speech intelligibility of surgical patients who have had parts of their articulators removed. Because of the removal of parts of the articulator, a patient's speech may be distorted and difficult to understand. To overcome this problem, VC methods can be applied to convert the distorted speech such that it is clear and more intelligible. To design an effective VC method, two key points must be considered: 1) the amount of training data may be limited (because speaking for a long time is usually difficult for postoperative patients); 2) rapid conversion is desirable (for better communication). Methods: We propose a novel joint dictionary learning based non-negative matrix factorization (JD-NMF) algorithm. Compared to conventional VC techniques, JD-NMF can perform VC efficiently and effectively with only a small amount of training data. Results: The experimental results demonstrate that the proposed JD-NMF method not only achieves notably higher short-time objective intelligibility (STOI) scores (a standardized objective intelligibility evaluation metric) than those obtained using the original unconverted speech but is also significantly more efficient and effective than a conventional exemplar-based NMF VC method. Conclusion: The proposed JD-NMF method may outperform the state-of-the-art exemplar-based NMF VC method in terms of STOI scores under the desired scenario. Significance: We confirmed the advantages of the proposed joint training criterion for the NMF-based VC. Moreover, we verified that the proposed JD-NMF can effectively improve the speech intelligibility scores of oral surgery patients.Objective: This paper focuses on machine learning based voice conversion (VC) techniques for improving the speech intelligibility of surgical patients who have had parts of their articulators removed. Because of the removal of parts of the articulator, a patient's speech may be distorted and difficult to understand. To overcome this problem, VC methods can be applied to convert the distorted speech such that it is clear and more intelligible. To design an effective VC method, two key points must be considered: 1) the amount of training data may be limited (because speaking for a long time is usually difficult for postoperative patients); 2) rapid conversion is desirable (for better communication). Methods: We propose a novel joint dictionary learning based non-negative matrix factorization (JD-NMF) algorithm. Compared to conventional VC techniques, JD-NMF can perform VC efficiently and effectively with only a small amount of training data. Results: The experimental results demonstrate that the proposed JD-NMF method not only achieves notably higher short-time objective intelligibility (STOI) scores (a standardized objective intelligibility evaluation metric) than those obtained using the original unconverted speech but is also significantly more efficient and effective than a conventional exemplar-based NMF VC method. Conclusion: The proposed JD-NMF method may outperform the state-of-the-art exemplar-based NMF VC method in terms of STOI scores under the desired scenario. Significance: We confirmed the advantages of the proposed joint training criterion for the NMF-based VC. Moreover, we verified that the proposed JD-NMF can effectively improve the speech intelligibility scores of oral surgery patients.

Modulation of the stemness and osteogenic differentiation of human mesenchymal stem cells by controlling RGD concentrations of poly(carboxybetaine) hydrogel.

In vitro modulation of the differentiation status of mesenchymal stem cells (MSCs) is important for their application to regenerative medicine. We suggested that the morphology and differentiation states of MSCs could be modulated by controlling the cell affinity of a substrate. The objective of this study was to investigate the effects of surface bio-adhesive signals on self-renewal and osteogenic differentiation of MSCs using a low-fouling platform. Cell-resistant poly(carboxybetaine) hydrogel was conjugated with 5 µM or 5 mM of cell-adhesive arginine-glycine-aspartic acid (RGD) peptides in order to control the cells' affinity to the substrate. Human mesenchymal stem cells (hMSCs) were cultured on the RGD-modified poly(carboxybetaine) hydrogel and then the cells' states of stemness and osteogenic differentiation were evaluated using reverse-transcriptase polymerase chain reaction. The hMSCs formed three-dimensional spheroids on the 5 µM RGD substrate, while cells on the 5 mM RGD substrate exhibited spreading morphology. Furthermore, cells on the 5 µM RGD hydrogel maintained a better stemness phenotype, while the hMSCs on the 5 mM RGD hydrogel proliferated faster and underwent osteogenic differentiation. In conclusion, the stemness of hMSCs was best maintained on a low RGD surface, while osteogenic differentiation of hMSCs was enhanced on a high RGD surface.

Fabrication of poly(N-isopropylacrylamide) films containing submicrometer grooves for constructing aligned cell sheets.

Transplantation of cell sheets including an intact extracellular matrix is one tissue-engineering strategy for tissue regeneration. Temperature-responsive substrates based on poly(N-isopropylacrylamide) (PNIPAAm) have been used to harvest intact cell sheets by temperature change. In this work, we immobilized PNIPAAm on plastic substrates by a UV-activated azide-based cross-linking mechanism. We demonstrated that the UV-cross-linked PNIPAAm films could respond to temperature changes and be used for cell-sheet fabrication. Next, grooved PNIPAAm substrates were fabricated by imprinting from grooved poly(dimethylsiloxane) (PDMS) molds (800 nm in groove width and 500 nm in depth). C2C12 cells formed aligned cell sheets on the grooved PNIPAAm surface. The aligned cell sheet could be transferred to a gelatin substrate without losing cell alignment. We expect that this simple time-saving technique for the fabrication of grooved PNIPAAm substrates will benefit from the application of cellular alignment in tissue-engineering products.