A Real-Time Speech Separation Method Based on Camera and Microphone Array Sensors Fusion Approach.

In the context of assisted human, identifying and enhancing non-stationary speech targets speech in various noise environments, such as a cocktail party, is an important issue for real-time speech separation. Previous studies mostly used microphone signal processing to perform target speech separation and analysis, such as feature recognition through a large amount of training data and supervised machine learning. The method was suitable for stationary noise suppression, but relatively limited for non-stationary noise and difficult to meet the real-time processing requirement. In this study, we propose a real-time speech separation method based on an approach that combines an optical camera and a microphone array. The method was divided into two stages. Stage 1 used computer vision technology with the camera to detect and identify interest targets and evaluate source angles and distance. Stage 2 used beamforming technology with microphone array to enhance and separate the target speech sound. The asynchronous update function was utilized to integrate the beamforming control and speech processing to reduce the effect of the processing delay. The experimental results show that the noise reduction in various stationary and non-stationary noise environments were 6.1 dB and 5.2 dB respectively. The response time of speech processing was less than 10ms, which meets the requirements of a real-time system. The proposed method has high potential to be applied in auxiliary listening systems or machine language processing like intelligent personal assistant.

Risk factors for internal carotid artery injury in adults during simple nasopharyngeal surgeries.

The purpose of this study attempted to analyze the potential risk factors for internal carotid artery injury during simple nasopharyngeal surgeries with or without an endoscopic aid. One hundred and seventy magnetic resonance imaging scans (340 halves) of the brain were retrospectively reviewed and studied. Anatomic variations of carotid arteries were classified, and various distances from the internal carotid arteries to the nasopharyngeal subsites were directly measured on the scans. The mean distances between the internal carotid arteries and nasopharyngeal subsites were significantly shortened in patients with nasopharyngeal internal carotid artery aberrancy, female gender, and lower body weight. The distance to the posterior nasopharyngeal wall was also shortened with age. However, the severity of nasopharyngeal carotid artery variations (kinking and coiling) did not reflect the shortening of mean distances to nasopharyngeal subsites. In conclusion, from multiple linear regression analysis, we found that the risk of an internal carotid artery injury during simple nasopharyngeal surgeries with or without an endoscopic aid is greatest in adult patients with nasopharyngeal carotid artery aberrancy, followed by female gender, lower body weight, and increasing age.

Increased risk of deep neck infection among HIV-infected patients in the era of highly active antiretroviral therapy--a population-based follow-up study.

BACKGROUND: Deep neck infections (DNIs) in HIV-infected patients often produce severe complications, even death. Data on the incidence rates and risks of DNI among HIV-infected patients are scarce, particularly with the widespread use of highly active antiretroviral therapy (HAART). We evaluated the incidence rates and risks for DNI among HIV-infected patients and observed the long-term trends. METHODS: A total of 9888 new HIV-infected patients diagnosed in 2001-2007 were included and matched with 49440 randomly selected subjects. The HIV-infected subjects were offered free access to HAART. All subjects were traced until December 2009. A Kaplan-Meier analysis generated the cumulative DNI incidence rate. The adjusted hazard ratio was computed using Cox proportional hazard regressions. RESULTS: From the HIV-infected and comparison cohorts, 222 individuals (57.01 cases per 10000 person-years) and 735 individuals (35.54 cases per 10000 person-years) developed DNI, respectively. The log rank test indicated that patients with HIV had a significantly higher 8-year incidence rate of DNI than the control group (P < 0.0001). The adjusted hazard ratio for developing DNI after an HIV attack during the mean 3.94 years follow-up period was 1.59. The incidence rate and relative risk of DNI were 74.58 (per 10000 person-years) and 2.05 (P < 0.0001). Both figures were highest in the first follow-up year and decreased year-by-year thereafter. CONCLUSION: The risk of developing DNI is significantly elevated among HIV-infected patients, even with free access to HAART. Additional research is needed to examine the role of HAART in reducing the risk.

Development of Novel Hearing Aids by Using Image Recognition Technology.

Speech is easily affected by different background noise in real environment to reduce the speech intelligibility, in particular, for hearing impaired listeners. In order to improve the above issue, several hearing aids have been developed to enhance the speech signal in noisy environment. Most of current hearing aids were designed to enhance the component of speech and suppress the component of noise. However, it is difficult to separate other speech sources. Adaptive signal enhancement with the beamforming technique might improve the above issue. However, how to distinguish the location of the desired speaker effectively is still a difficult challenge for adaptive beamforming method. A novel concept of hearing aid was proposed in this study. Different from the beamforming-based hearing aids, which use the cross-correlation-coefficient method to estimate time difference of arrival (TDOA), an image recognition technology was used to estimate the location of the desired speaker to obtain the more precise TDOA. An adaptive signal enhancement was also used to enhance the noisy speech sound. From the experimental results, the proposed system could provide a smaller absolute error of TDOA less than 1.25 × 10-4 ms, and a clear speech sound from the target speaker who the user wants to listen to.

Comparison between open partial laryngectomy with tube-free tracheostomy and total laryngectomy for hypopharyngeal cancer with cartilage invasion.

The present study aimed to identify a feasible treatment strategy for hypopharyngeal cancer (HPC) with non-extensive invasion of the thyroid and/or cricoid cartilage. Between June 2008 and December 2014, patients with previously untreated HPC invading cartilage who had received either open partial laryngectomy (OPL) with tube-free tracheostomy or total laryngectomy (TL) with permanent tracheostomy and an artificial larynx (pneumatic tube) were retrospectively reviewed. The patients with extensive cartilage invasion and those with inoperable or T4b disease were excluded for OPL. Outcomes and quality of life were compared between the two treatment modalities. A total of 44 patients were included. The survival rates, complications, and Dysphagia Score were compared between the two treatment modalities. The outcome of the Voice Handicap Index (P=0.032), understandability of speech (P<0.001), normalcy of diet (P=0.041), senses (P=0.006), speech (P<0.001) and social contact (P=0.004) were significantly improved in the group receiving OPL compared with the group receiving TL. Therefore, OPL with tube-free tracheostomy may be a feasible option to treat patients with HPC with non-extensive invasion of the thyroid and/or cricoid cartilage.

Radial forearm and forehead flap reconstruction following resection of a nasal arteriovenous malformation: A case report.

Arteriovenous malformation (AVM) is a structural vascular abnormality in which the arterial vasculature connects with the venous vasculature without capillary connections. AVM confined to the nasal cavity is considerably rare. Blurred vision can be one of the associated symptoms. A combined approach of complete surgical resection with prior superselective embolization is the treatment of choice. Following resection, the reconstruction of facial defects, particularly in the nasal area, is challenging. The present study reports the rare case of a patient with an AVM in the nasal cavity, in which embolization, resection and flap reconstruction were performed. Embolization and complete surgical resection were used to avoid recurrence. Subsequently, a combination of free radial forearm and forehead flaps was used for the reconstruction of the nasal defect, without prosthesis. To the best of our knowledge, this is the first report of AVM confined to the nasal cavity, managed by a combination of free radial forearm and forehead flap reconstruction following complete resection. The cosmetic results of the procedure were acceptable.

Effect of carotid artery aberrancy on the distance between the vessel and nasopharyngeal subsites.

BACKGROUND: Life-threatening hemorrhaging due to nasopharyngeal internal carotid artery (ICA) aberrancy may occur during routine nasopharyngeal surgery. To understand better the potential adverse effect of nasopharyngeal ICA aberrancy on routine nasopharyngeal surgery, we classified aberrant nasopharyngeal ICAs and analyzed the differences in mean distances from the ICA to nasopharyngeal subsites between aberrant and nonaberrant vessels. METHODS: The courses of nasopharyngeal ICAs were examined and classified for an aberrant pathway. Various distances were measured on magnetic resonance brain scans. The mean values of the measured variables were compared using an unpaired two-sample t test. RESULTS: The mean distances to the torus tubarius, the opening of Rosenmuller's fossa, and the posterior nasopharyngeal wall were 19.6 mm, 15.8 mm, and 16.7 mm, respectively, in the aberrant case group, and 23.1 mm (p < 0.001), 19.8 mm (p < 0.001), and 20.7 mm (p < 0.001) in the nonaberrant control group. CONCLUSION: The mean distances between the ICA and nasopharyngeal subsites were significantly shortened (by 15-21%) in the presence of aberrant nasopharyngeal segments, which may increase the risk of severe complications in common and uncomplicated nasopharyngeal surgery, such as adenoidectomy, eustachian tuboplasty, and nasopharyngeal biopsies. However, the mean distances were not shortened by the severity (kinking and coiling) of the aberrant nasopharyngeal carotid arteries.

Manganese superoxide dismutase and glutathione peroxidase as prognostic markers in patients with buccal mucosal squamous cell carcinomas.

BACKGROUND: We investigated the relationship of the immunohistochemical expression status of manganese superoxide dismutase (MnSOD), catalase, glutathione peroxidase (GPx), and myeloperoxidase (MPO) in buccal mucosal squamous cell carcinoma (SCC) with clinicopathologic parameters and prognosis. METHODS: The expression status of MnSOD, GPx, catalase, and MPO was evaluated by immunohistochemistry in a series of 216 surgically resected buccal mucosal SCC specimens, using tissue microarray slides. RESULTS: MnSOD, GPx, catalase, and MPO were commonly expressed in buccal mucosal SCC. The high expression level of MnSOD was associated with better disease-specific survival (p = .009), especially for patients in moderate or poor cell differentiation (p = .045), pathologic stage I (p = .002) and postoperative radiotherapy (p = .048). The high expression level of GPx was also correlated with better disease-specific survival (p = .042), especially for patients in pathologic stage IV (p = .010) and postoperative radiotherapy (p = .018). CONCLUSIONS: MnSOD and GPx are significant prognostic factors for favorable survival in patients with buccal mucosal SCC.