Automatic hypernasality grade assessment in cleft palate speech based on the spectral envelope method.
- 作者列表："Zhang J","Yang S","Wang X","Tang M","Yin H","He L
:Due to velopharyngeal incompetence, airflow overflows from the oral cavity to the nasal cavity, which results in hypernasality. Hypernasality greatly reduces speech intelligibility and affects the daily communication of patients with cleft palate. Accurate assessment of hypernasality grades can provide assisted diagnosis for speech-language pathologists (SLPs) in clinical settings. Utilizing a support vector machine (SVM), this paper classifies speech recordings into four grades (normal, mild, moderate and severe hypernasality) based on vocal tract characteristics. Linear prediction (LP) analysis is widely used to model the vocal tract. Glottal source information may be included in the LP-based spectrum. The stabilized weighted linear prediction (SWLP) method, which imposes the temporal weights on the closed-phase interval of the glottal cycle, is a more robust approach for modeling the vocal tract. The extended weighted linear prediction (XLP) method weights each lagged speech signal separately, which achieves a finer time scale on the spectral envelope than the SWLP method. Tested speech recordings were collected from 60 subjects with cleft palate and 20 control subjects, and included a total of 4640 Mandarin syllables. The experimental results showed that the spectral envelope of normal speech decreases faster than that of hypernasal speech in the high-frequency part. The experimental results also indicate that the SWLP- and XLP-based methods have smaller correlation coefficients between normal and hypernasal speech than the LP method. Thus, the SWLP and XLP methods have better ability to distinguish hypernasal from normal speech than the LP method. The classification accuracies of the four hypernasality grades using the SWLP and XLP methods range from 83.86% to 97.47%. The selection of the model order and the size of the weight function are also discussed in this paper.
: 由于腭咽闭合不全，气流从口腔溢出到鼻腔，导致鼻过度。鼻过度大大降低了语音清晰度，影响了腭裂患者的日常交流。准确评估多鼻症分级可为临床环境中的言语-语言病理学家 (SLPs) 提供辅助诊断。利用支持向量机 (SVM)，根据声道特征，将语音记录分为四个等级 (正常、轻度、中度和重度高鼻音)。线性预测 (LP) 分析被广泛用于声带的建模。Glottal来源信息可能包含在基于LP的光谱中。稳定加权线性预测 (SWLP) 方法，对声门周期的闭合相位间隔施加时间权重，是一种更稳健的声带建模方法。扩展加权线性预测 (XLP) 方法分别对每个滞后语音信号进行加权，比SWLP方法在谱包络上实现了更精细的时间尺度。从 60 例腭裂受试者和 20 例对照受试者中收集测试的语音记录，共包括 4640 个普通话音节。实验结果表明，在高频部分，正常语音的频谱包络比高鼻语音的频谱包络降低更快。实验结果还表明，基于SWLP和XLP的方法与LP方法相比，正常和超鼻语音之间的相关系数较小。因此，SWLP和XLP方法比LP方法具有更好的区分鼻高音和正常语音的能力。使用SWLP和XLP方法的四种鼻部分级的分类精度范围为 83.86% 至 97.47%。本文还讨论了模型阶数的选择和权函数的大小。
METHODS:BACKGROUND:The anterior oronasal fistulae neighboring the alveolar cleft could persist or reappear after the alveolar reconstruction with cancellous bone grafting. The persistent symptomatic anterior oronasal fistulae need to be repaired, but surgery remains a challenge in cleft care. Surprisingly, this issue has rarely been reported in the literature. The purpose of this long-term study was to report a single surgeon experience with a therapeutic protocol for persistent symptomatic anterior oronasal fistula repair. METHODS:This is a retrospective study of consecutive patients with Veau type III and IV clefts and persistent symptomatic anterior oronasal fistulae managed according to a therapeutic protocol from 1997 to 2018. Depending on fistula size, patients were treated with local flaps associated with an interpositional graft or two-stage tongue flaps (small/medium or large fistulae, respectively). The surgical outcomes were classified as "good" (complete fistula closure with no symptoms), "fair" (asymptomatic narrow fistula remained), or "poor" (failure with persistent symptoms). RESULTS:Forty-four patients with persistent symptomatic anterior oronasal fistulae were reconstructed with local flaps associated with interpositional fascia or dermal fat grafting (52.3%) or two-stage tongue flaps (47.7%). Most of patients (93.2%) presented "good" outcomes, ranging from 87% to 100% (local and tongue flaps, respectively). Three (6.8%) patients presented symptomatic residual fistula ("poor" outcomes). CONCLUSIONS:For the repair of persistent symptomatic anterior oronasal fistulae, this therapeutic protocol provided satisfactory outcome with low fistula recurrence rate.
METHODS:OBJECTIVE:Methadone is a vital treatment for women with opioid use disorder in pregnancy. Previous reports suggested an association between methadone exposure and Pierre Robin sequence (PRS), a rare craniofacial anomaly. We assessed the association between gestational methadone exposure and PRS. DESIGN/SETTING:This case-malformed control study used European Surveillance of Congenital Anomalies population-based registries in Ireland, the Netherlands, Italy, Switzerland, Croatia, Malta, Portugal, Germany, Wales, Norway and Spain, 1995-2011. PATIENTS:Cases included PRS based on International Classification of Disease (ICD), Ninth Edition-British Paediatric Association (BPA) code 75 603 or ICD, Tenth Edition-BPA code Q8708. Malformed controls were all non-PRS anomalies, excluding genetic conditions, among live births, fetal deaths from 20 weeks' gestation and terminations of pregnancy for fetal anomalies. An exploratory analysis assessed the association between methadone exposure and other congenital anomalies (CAs) excluding PRS. Methadone exposure was ascertained from medical records and maternal interview. RESULTS:Among 87 979 CA registrations, there were 127 methadone-exposed pregnancies and 336 PRS cases. There was an association between methadone exposure and PRS (OR adjusted for registry 12.3, 95% CI 5.7 to 26.8). In absolute terms, this association reflects a risk increase from approximately 1-12 cases per 10 000 births. A raised OR was found for cleft palate (adjusted OR 5.0, 95% CI 2.7 to 9.2). CONCLUSIONS:These findings suggest that gestational methadone exposure is associated with PRS. The association may be explained by unmeasured confounding factors. The small increased risk of PRS in itself does not alter the risk-benefit balance for gestational methadone use. The association with cleft palate, a more common CA, should be assessed with independent data.
METHODS::Orthopedic treatment to improve deficient maxillary growth of cleft lip and palate patients is an important part of treatment. The success of this treatment is strongly dependent on the time of initiation of therapy. There has been a large controversy in the available literature regarding the skeletal age of these patients. The aim of the present study was to compare the skeletal age of cleft lip and palate patients with normal individuals.37 unilateral and 14 bilateral cleft lip and palate patients and 47 healthy individuals participated in this cross-sectional study. The patients were classified into 8 to 10 and 11 to 14-year-old individuals. Cervical vertebral maturational stage of participants was evaluated in the lateral cephalometry. The skeletal age of cleft lip and palate patients was compared with normal controls. Chi-square was used for statistical analysis. There was not a significant difference in the skeletal developmental stage of unilateral and bilateral cleft compared to their normal peers according to their age and sex. Also, significant difference in skeletal maturational stage of cleft lip and palate patients was not found between boys and girls (P = 0.8). Similarly, no significant difference was found in the skeletal age of the 3 studied groups without considering the age and sex of participants (P = 0.5). Regarding the similar skeletal maturational stage of cleft lip and palate patients with normal controls in our study, their maxillofacial orthopedic treatment can be initiated at similar time to normal peers.