The loss of speech function due to conditions such as laryngectomy and vocal cord paralysis significantly impacts the quality of life for patients.Achieving effective communication for these patients is a goal pursued...The loss of speech function due to conditions such as laryngectomy and vocal cord paralysis significantly impacts the quality of life for patients.Achieving effective communication for these patients is a goal pursued by researchers.This study primarily explores a method for reconstructing Mandarin speech based on voice-related neck and facial surface electromyography(sEMG).Neck and facial sEMG signals and speech waveform were synchronously collected during normal speech production.A speech reconstruction model for Mandarin speech,based on multi-scale feature extraction from EMG and a generative adversarial network(GAN),was developed.Both subjective and objective evaluations were conducted to assess the speech reconstruction performance of the model.The evaluation results indicate that the model effectively reconstructs speech from neck and facial sEMG signals.The reconstructed speech closely matches the original in terms of spectrogram and fundamental frequency,with mel-cepstrum distortion of 8.45 dB,log F0 RMSE of 0.40,F0 correlation coefficient of 0.71 and F0 voiced/unvoiced estimation accuracy of 0.80.The character error rate of the reconstructed speech is 0.32,while the tone error rate is 0.26.The subjective listening test results show that the naturalness of the reconstructed speech is acceptable,with a mean opinion score greater than 3.This study demonstrates the potential of deep learning techniques in effectively reconstructing Mandarin speech from sEMG.展开更多
Oral squamous cell carcinoma is one of the most common malignant tumours in the oral and maxillofacial regions and is highly malignant and prone to recur despite the development of various effective treatments,includi...Oral squamous cell carcinoma is one of the most common malignant tumours in the oral and maxillofacial regions and is highly malignant and prone to recur despite the development of various effective treatments,including surgery and chemoradiotherapy.Actually,it is difficult to ensure the complete elimination of tumour cells,and maxillofacial bone defects caused by surgery are hard to heal by themselves.In addition,chemoradiotherapy can bring serious side-effects.Therefore,it is imperative to develop a postoperative therapy to kill residual squamous cancer cells and repair bone defects without any side-effects.Here,we prepared a 3D scaffold by a 3D printing technique and freeze-drying method,which contained collagen,silk and hydroxyapatite(CSH)and was functionalized with MXene nanosheets(M-CSH).The considerable photothermal effect with long-term stability can significantly kill squamous CAL-27 cancer cells in vitro and inhibit tumour growth in vivo,increasing the probability of the M-CSH scaffold being applied in the photothermal therapy of oral squamous cell carcinoma.Moreover,the cell proliferation-and osteogenic-related protein expression of mouse embryonic osteogenic precursors(MC3T3-E1)indicated excellent biocompatibility and osteogenic activity of M-CSH scaffolds.The good compression modulus(52.8362.25 kPa)and in vivo bone formation performance made it possible to be used as reconstructive materials for bone defects.This scaffold is likely promising in future tissue engineering,especially for the multifunctional treatment of maxillofacial tumours.展开更多
基金supported by the National Natural Science Foundation of China,China(Grant 12372299 and Grant 32071315)partly supported by JST CREST,Japan(Grant JPMJCR19A3).
文摘The loss of speech function due to conditions such as laryngectomy and vocal cord paralysis significantly impacts the quality of life for patients.Achieving effective communication for these patients is a goal pursued by researchers.This study primarily explores a method for reconstructing Mandarin speech based on voice-related neck and facial surface electromyography(sEMG).Neck and facial sEMG signals and speech waveform were synchronously collected during normal speech production.A speech reconstruction model for Mandarin speech,based on multi-scale feature extraction from EMG and a generative adversarial network(GAN),was developed.Both subjective and objective evaluations were conducted to assess the speech reconstruction performance of the model.The evaluation results indicate that the model effectively reconstructs speech from neck and facial sEMG signals.The reconstructed speech closely matches the original in terms of spectrogram and fundamental frequency,with mel-cepstrum distortion of 8.45 dB,log F0 RMSE of 0.40,F0 correlation coefficient of 0.71 and F0 voiced/unvoiced estimation accuracy of 0.80.The character error rate of the reconstructed speech is 0.32,while the tone error rate is 0.26.The subjective listening test results show that the naturalness of the reconstructed speech is acceptable,with a mean opinion score greater than 3.This study demonstrates the potential of deep learning techniques in effectively reconstructing Mandarin speech from sEMG.
基金supported by the Tianjin Science and Technology Project(19ZXDBSY00070)the National Natural Science Foundation of China(11972198)the Special Project of Tianjin Clinical Medicine Key Discipline(HWZX001).
文摘Oral squamous cell carcinoma is one of the most common malignant tumours in the oral and maxillofacial regions and is highly malignant and prone to recur despite the development of various effective treatments,including surgery and chemoradiotherapy.Actually,it is difficult to ensure the complete elimination of tumour cells,and maxillofacial bone defects caused by surgery are hard to heal by themselves.In addition,chemoradiotherapy can bring serious side-effects.Therefore,it is imperative to develop a postoperative therapy to kill residual squamous cancer cells and repair bone defects without any side-effects.Here,we prepared a 3D scaffold by a 3D printing technique and freeze-drying method,which contained collagen,silk and hydroxyapatite(CSH)and was functionalized with MXene nanosheets(M-CSH).The considerable photothermal effect with long-term stability can significantly kill squamous CAL-27 cancer cells in vitro and inhibit tumour growth in vivo,increasing the probability of the M-CSH scaffold being applied in the photothermal therapy of oral squamous cell carcinoma.Moreover,the cell proliferation-and osteogenic-related protein expression of mouse embryonic osteogenic precursors(MC3T3-E1)indicated excellent biocompatibility and osteogenic activity of M-CSH scaffolds.The good compression modulus(52.8362.25 kPa)and in vivo bone formation performance made it possible to be used as reconstructive materials for bone defects.This scaffold is likely promising in future tissue engineering,especially for the multifunctional treatment of maxillofacial tumours.
