Preliminary observation of speech disorder in obstructive and mixed sleep apnea

Estimating the severity of obstructive sleep apnea during wakefulness using speech: A review

Obstructive sleep apnea (OSA) is a chronic breathing disorder during sleep that affects 10-30% of adults in North America. The gold standard for diagnosing OSA is polysomnography (PSG). However, PSG has several drawbacks, for example, it is a cumbersome and expensive procedure, which can be quite inconvenient for patients. Additionally, patients often have to endure long waitlists before they can undergo PSG. As a result, other alternatives for screening OSA have gained attention. Speech, as an accessible modality, is generated by variations in the pharyngeal airway, vocal tract, and soft tissues in the pharynx, which shares similar anatomical structures that contribute to OSA. Consequently, in this study, we aim to provide a comprehensive review of the existing research on the use of speech for estimating the severity of OSA. In this regard, a total of 851 papers were initially identified from the PubMed database using a specified set of keywords defined by population, intervention, comparison and outcome (PICO) criteria, along with a concatenated graph of the 5 most cited papers in the field extracted from ConnectedPapers platform. Following a rigorous filtering process that considered the preferred reporting items for systematic reviews and meta-analyses (PRISMA) approach, 32 papers were ultimately included in this review. Among these, 28 papers primarily focused on developing methodology, while the remaining 4 papers delved into the clinical perspective of the association between OSA and speech. In the next step, we investigate the physiological similarities between OSA and speech. Subsequently, we highlight the features extracted from speech, the employed feature selection techniques, and the details of the developed models to predict OSA severity. By thoroughly discussing the current findings and limitations of studies in the field, we provide valuable insights into the gaps that need to be addressed in future research directions.

Association between obstructive sleep apnea and risk of Benign vocal fold lesions: A nationwide 9-year follow-up cohort study

Since obstructive sleep apnea (OSA) affects various parts of the body, there has been little interest about the effect of OSA on voice. The objective of this study was to evaluate the risk of benign vocal fold lesions (BVFL) in OSA patients. This study used data from the National Health Insurance Service (NHIS) database. The study group was defined as the group diagnosed with OSA between 2008 and 2011. Non-OSA groups were selected based on propensity score (PS) matching. Incidence of BVFL among participants during the follow-up was analyzed. Cox proportional hazard regression analyses were performed to evaluate the association between OSA and incident BVFL. The HR value of the OSA group calculated by considering 8 variables indicates that the risk of developing BVFL is 79% higher than that of the control group. Further, among OSA patients, patients with a history of OP had a 35% lower risk of developing BVFL. The relationships between BVFL and 7 individual variables considered were as follows: For age, HR for the 40 to 59 years group was 1.20 (95%CI, 1.09-1.32). For sex, the HR in the female group was 1.22 (95%CI, 1.10-1.35). For residential areas, the HR values for "Seoul" 1.39 (95%CI, 1.23-1.59). In the high economic status group, the HR was 1.10 (95%CI, 1.01-1.21). This observational study indicated that OSA is associated with an increased incidence of BVFL. The incidence of BVFL increased with older age, female sex, and high SES.

A pilot observation using ultrasonography and vowel articulation to investigate the influence of suspected obstructive sleep apnea on upper airway

Failure to employ suitable measures before administering full anesthesia to patients with obstructive sleep apnea (OSA) who are undergoing surgery may lead to developing complications after surgery. Therefore, it is very important to screen OSA before performing a surgery, which is currently done by subjective questionnaires such as STOP-Bang, Berlin scores. These questionnaires have 10-36% specificity in detecting sleep apnea, along with no information given on anatomy of upper airway, which is important for intubation. To address these challenges, we performed a pilot study to understand the utility of ultrasonography and vowel articulation in screening OSA. Our objective was to investigate the influence of OSA risk factors in vowel articulation through ultrasonography and acoustic features analysis. To accomplish this, we recruited 18 individuals with no risk of OSA and 13 individuals with high risk of OSA and asked them to utter vowels, such as /a/ (as in "Sah"), /e/ (as in "See"). An expert ultra-sonographer measured the parasagittal anterior-posterior (PAP) and transverse diameter of the upper airway. From the recorded vowel sounds, we extracted 106 features, including power, pitch, formant, and Mel frequency cepstral coefficients (MFCC). We analyzed the variation of the PAP diameters and vowel features from "See: /i/" to "Sah /a/" between control and OSA groups by two-way repeated measures ANOVA. We found that, there was a variation of upper airway diameter from "See" to "Sah" was significantly smaller in OSA group than control group (OSA: ∆12.8 ± 5.3 mm vs. control: ∆22.5 ± 3.9 mm OSA, p < 0.01). Moreover, we found several vowel features showed the exact same or opposite trend as PAP diameter variation, which led us to build a machine learning model to estimate PAP diameter from vowel features. We found a correlation coefficient of 0.75 between the estimated and measured PAP diameter after applying four estimation models and combining their output with a random forest model, which showed the feasibility of using acoustic features of vowel sounds to monitor upper airway diameter. Overall, this study has proven the concept that ultrasonography and vowel sounds analysis may be useful as an easily accessible imaging tool of upper airway.

Executive Functioning, Language, and Behavioral Abilities Related to Obstructive Sleep Apnea in Down Syndrome

OBJECTIVES

Obstructive sleep apnea (OSA) is highly prevalent among individuals with Down syndrome (DS), and the nonphysiological consequences of OSA require examination to inform treatment planning. This study aimed to investigate the association between OSA and aspects of language, executive functioning, behavioral, social abilities, and sleep problems in youth with DS aged 6 to 17 years.

METHODS

Multivariate analysis of covariance was used to compare 3 groups adjusted for age, participants with DS with untreated OSA (n = 28), participants with DS without OSA (n = 38), and participants with DS with treated OSA (n = 34). To be eligible for the study, participants had to have an estimated mental age of 3 years. No children were excluded based on estimated mental age.

RESULTS

After adjusting for age, participants with untreated OSA showed a common pattern of lower estimated marginal mean scores than those with treated OSA and those with no OSA in expressive and receptive vocabulary and higher estimated marginal mean scores with executive functions, everyday memory, attention, internalizing and externalizing behavior, social behavior, and sleep problems. However, only the group differences for executive function (emotional regulation) and internalizing behavior were statistically significant.

CONCLUSION

Study findings corroborate and extend prior findings related to OSA and clinical outcomes for youth with DS. The study highlights the importance of OSA treatment in youth with DS and provides clinical recommendations for this population. Additional studies are necessary to control the effects of health and demographic variables.

A case for the role of memory consolidation in speech-motor learning

This review will explore the role of memory consolidation in speech-motor learning. Existing frameworks of speech-motor control account for the protracted time course of building the speech-motor representation. These perspectives converge on the speech-motor representation as a multimodal unit that is comprised of auditory, motor, and linguistic information. Less is known regarding the memory mechanisms that support the emergence of a generalized speech-motor unit from instances of speech production. Here, we consider the broader learning and memory consolidation literature and how it may apply to speech-motor learning. We discuss findings from relevant domains on the stabilization, enhancement, and generalization of learned information. Based on this literature, we provide our predictions for the division of labor between conscious and unconscious memory systems in speech-motor learning, and the subsequent effects of time and sleep to memory consolidation. We identify both the methodological challenges, as well as the practical importance, of advancing this work empirically. This discussion provides a foundation for building a memory-based framework for speech-motor learning.

Voice Disorders in Obstructive Sleep Apnea: Prevalence, Risk Factors, and the Role of CPAP

OBJECTIVE

Obstructive sleep apnea (OSA) is characterized by frequent interruptions in breathing related to upper airway collapse during sleep and may adversely affect phonatory function. This study aimed to: (1) establish the prevalence, risks, and quality of life burden of voice disorders in OSA and (2) explore the relation between voice disorders and positive airway pressure (PAP) therapy.

STUDY DESIGN

Cross-sectional, descriptive epidemiology study.

METHODS

Analyses were based on 94 individuals with OSA (53 men, 41 women; mean age = 54.7 ± 12.8 years) who completed a telephone interview.

RESULTS

Twenty-eight percent of participants reported having a current voice disorder. Of those with a current voice disorder, 83% had experienced symptoms for at least a year, and 58% had symptoms for at least 4 years. The prevalence of a current voice disorder was greater in women than men (44% vs 15%, P = .0020) but did not vary significantly across different age groups, body mass index (BMI), apnea/hypopnea index (AHI) severity, or medical history. After adjusting for sex, consistent use of PAP therapy (with humidification) was associated with (1) lower occurrence of voice disorders in women (Mantel-Haenszel [MH] χ²P = .0195), (2) reduced snoring severity accompanied by fewer voice disorders in men (MH χ²P = .0101), and (3) fewer reports of acid reflux as a possible trigger for voice problems (MH χ²P = .0226). Patients with OSA who also had a current voice disorder experienced lower overall quality of life compared to those without.

CONCLUSIONS

Chronic, longstanding voice disorders are common in women with OSA and produce significant adverse effects on quality of life. Nightly PAP use (with humidification) was associated with fewer voice symptoms and reduced severity of snoring and acid reflux as possible contributors. Further research is necessary to better understand the origin of these voice disorders in OSA and their potential response to treatment.

Obstructive Sleep Apnea in Women: Study of Speech and Craniofacial Characteristics

Background

Obstructive sleep apnea (OSA) is a common sleep disorder characterized by frequent cessation of breathing lasting 10 seconds or longer. The diagnosis of OSA is performed through an expensive procedure, which requires an overnight stay at the hospital. This has led to several proposals based on the analysis of patients’ facial images and speech recordings as an attempt to develop simpler and cheaper methods to diagnose OSA.

Objective

The objective of this study was to analyze possible relationships between OSA and speech and facial features on a female population and whether these possible connections may be affected by the specific clinical characteristics in OSA population and, more specifically, to explore how the connection between OSA and speech and facial features can be affected by gender.

Methods

All the subjects are Spanish subjects suspected to suffer from OSA and referred to a sleep disorders unit. Voice recordings and photographs were collected in a supervised but not highly controlled way, trying to test a scenario close to a realistic clinical practice scenario where OSA is assessed using an app running on a mobile device. Furthermore, clinical variables such as weight, height, age, and cervical perimeter, which are usually reported as predictors of OSA, were also gathered.

Acoustic analysis is centered in sustained vowels. Facial analysis consists of a set of local craniofacial features related to OSA, which were extracted from images after detecting facial landmarks by using the active appearance models. To study the probable OSA connection with speech and craniofacial features, correlations among apnea-hypopnea index (AHI), clinical variables, and acoustic and facial measurements were analyzed.

Results

The results obtained for female population indicate mainly weak correlations (r values between .20 and .39). Correlations between AHI, clinical variables, and speech features show the prevalence of formant frequencies over bandwidths, with F2/i/ being the most appropriate formant frequency for OSA prediction in women. Results obtained for male population indicate mainly very weak correlations (r values between .01 and .19). In this case, bandwidths prevail over formant frequencies. Correlations between AHI, clinical variables, and craniofacial measurements are very weak.

Conclusions

In accordance with previous studies, some clinical variables are found to be good predictors of OSA. Besides, strong correlations are found between AHI and some clinical variables with speech and facial features. Regarding speech feature, the results show the prevalence of formant frequency F2/i/ over the rest of features for the female population as OSA predictive feature. Although the correlation reported is weak, this study aims to find some traces that could explain the possible connection between OSA and speech in women. In the case of craniofacial measurements, results evidence that some features that can be used for predicting OSA in male patients are not suitable for testing female population.

The effects of uvulopalatal flap operation on speech nasalance and the acoustic parameters of the final nasal consonants

OBJECTIVE

The acoustic characteristics of voice are determined by the source of the sound and shape of the vocal tract. Various anatomical changes after uvulopalatal flap (UPF) operation can change nasalance and/or other voice characteristics. Our aim was to explore the possible effects of UPF creation on speech nasalance and the resonatory features of the final nasal consonants, and thus voice characteristics.

METHODS

A total of 30 patients (26 males, 4 females) with obstructive sleep apnea who underwent UPF operation were recruited. A Nasometer II 3.4 instrument was used to assess nasalance pre- and post-operatively; the patients read standard Korean passages and the readings were recorded in Computer Speech Laboratory for later spectral analysis. Praat software was used to identify frequency bands affecting perioperative nasalance scores. Minima, maxima, and slopes were analyzed.

RESULTS

We found no significant correlation between nasalance scores (any passage) and the respiratory distress index or body mass index. No significant perioperative change in any nasalance score. The moment variations in the final consonants /m/ and /n/ did not change significantly postoperatively. However, the postoperative moment variation of the final consonant /ng/ differed significantly in the third formant (F3) and second bandwidth (BW2).

CONCLUSION

Few significant changes in nasal resonance speech quality were apparent after UPF operation. However, a postoperative acoustic change in the final sound /ng/ may be sustained. Patients may be preoperatively advised that the risk of voice change is very low, but not absent.

Reviewing the connection between speech and obstructive sleep apnea

BACKGROUND

Sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). The altered UA structure or function in OSA speakers has led to hypothesize the automatic analysis of speech for OSA assessment. In this paper we critically review several approaches using speech analysis and machine learning techniques for OSA detection, and discuss the limitations that can arise when using machine learning techniques for diagnostic applications.

METHODS

A large speech database including 426 male Spanish speakers suspected to suffer OSA and derived to a sleep disorders unit was used to study the clinical validity of several proposals using machine learning techniques to predict the apnea-hypopnea index (AHI) or classify individuals according to their OSA severity. AHI describes the severity of patients' condition. We first evaluate AHI prediction using state-of-the-art speaker recognition technologies: speech spectral information is modelled using supervectors or i-vectors techniques, and AHI is predicted through support vector regression (SVR). Using the same database we then critically review several OSA classification approaches previously proposed. The influence and possible interference of other clinical variables or characteristics available for our OSA population: age, height, weight, body mass index, and cervical perimeter, are also studied.

RESULTS

The poor results obtained when estimating AHI using supervectors or i-vectors followed by SVR contrast with the positive results reported by previous research. This fact prompted us to a careful review of these approaches, also testing some reported results over our database. Several methodological limitations and deficiencies were detected that may have led to overoptimistic results.

CONCLUSION

The methodological deficiencies observed after critically reviewing previous research can be relevant examples of potential pitfalls when using machine learning techniques for diagnostic applications. We have found two common limitations that can explain the likelihood of false discovery in previous research: (1) the use of prediction models derived from sources, such as speech, which are also correlated with other patient characteristics (age, height, sex,…) that act as confounding factors; and (2) overfitting of feature selection and validation methods when working with a high number of variables compared to the number of cases. We hope this study could not only be a useful example of relevant issues when using machine learning for medical diagnosis, but it will also help in guiding further research on the connection between speech and OSA.

Speech Signal and Facial Image Processing for Obstructive Sleep Apnea Assessment

Obstructive sleep apnea (OSA) is a common sleep disorder characterized by recurring breathing pauses during sleep caused by a blockage of the upper airway (UA). OSA is generally diagnosed through a costly procedure requiring an overnight stay of the patient at the hospital. This has led to proposing less costly procedures based on the analysis of patients' facial images and voice recordings to help in OSA detection and severity assessment. In this paper we investigate the use of both image and speech processing to estimate the apnea-hypopnea index, AHI (which describes the severity of the condition), over a population of 285 male Spanish subjects suspected to suffer from OSA and referred to a Sleep Disorders Unit. Photographs and voice recordings were collected in a supervised but not highly controlled way trying to test a scenario close to an OSA assessment application running on a mobile device (i.e., smartphones or tablets). Spectral information in speech utterances is modeled by a state-of-the-art low-dimensional acoustic representation, called i-vector. A set of local craniofacial features related to OSA are extracted from images after detecting facial landmarks using Active Appearance Models (AAMs). Support vector regression (SVR) is applied on facial features and i-vectors to estimate the AHI.

Automatic detection of obstructive sleep apnea using speech signals

Obstructive sleep apnea (OSA) is a common disorder associated with anatomical abnormalities of the upper airways that affects 5% of the population. Acoustic parameters may be influenced by the vocal tract structure and soft tissue properties. We hypothesize that speech signal properties of OSA patients will be different than those of control subjects not having OSA. Using speech signal processing techniques, we explored acoustic speech features of 93 subjects who were recorded using a text-dependent speech protocol and a digital audio recorder immediately prior to polysomnography study. Following analysis of the study, subjects were divided into OSA (n=67) and non-OSA (n=26) groups. A Gaussian mixture model-based system was developed to model and classify between the groups; discriminative features such as vocal tract length and linear prediction coefficients were selected using feature selection technique. Specificity and sensitivity of 83% and 79% were achieved for the male OSA and 86% and 84% for the female OSA patients, respectively. We conclude that acoustic features from speech signals during wakefulness can detect OSA patients with good specificity and sensitivity. Such a system can be used as a basis for future development of a tool for OSA screening.

The effect of uvulopalatopharyngoplasty on the nasality of voice

We prospectively studied the effect of uvulopalatopharyngoplasty (UPPP) on several speech and vocal parameters in 15 patients. Preoperative, 1-month postoperative, and 6-month postoperative assessments were made. Specific parameters included maximum phonation time, mean speaking fundamental frequency, mean frequency perturbation, intensity, and nasalance. Psychoacoustic analysis included pitch, quality, rate, resonance, and loudness. The primary outcome measure was the nasality of voice. At the 1-month postoperative assessment, one patient exhibited mild hypernasality by psychoacoustic analysis and a mildly elevated measured nasalance. At 6 months, both the psychoacoustic hypernasality and the measure nasalance had normalized. Consequently, no subjects exhibited hypernasality at the final assessment. Although abnormalities by psychoacoustic analysis were exhibited by 3 subjects at the 6-month postoperative assessment, none could be attributed to the surgery, but rather to concurrent illnesses. This study adds further data and support that UPPP done in standard fashion does not result in significant changes in voice either by measured parameters or by clinical assessment. Although this study does not obviate the need for preoperative counseling of patients about the potential effect of UPPP on voice, they can be counseled that the risk of hypernasality after UPPP is low.

Obstructive sleep apnea surgery: patient perspective and polysomnographic results

OBJECTIVE

The goal of this study was to assess the outcomes of obstructive sleep apnea (OSA) surgery based on the patient perspective and polysomnographic data.

STUDY DESIGN

Fifty-six patients with severe OSA completed the 2-phase reconstructive protocol. A minimum of 6 months after the phase II surgery and after the postoperative polysomnography, questionnaires with visual analog scales (VAS 0-10) were mailed to the patients to assess their perceptions of treatment results.

RESULTS

Forty-two (75%) questionnaires were returned. The mean patient age was 46.3 years. The mean respiratory disturbance index improved from 58.7 to 10.0. The mean lowest oxygen saturation improved from 76.3 to 87.3%. All 42 patients reported improved sleep (VAS 8.7). Although 10 patients reported changes in speech, the changes were insignificant, with 9 of the patients scoring 0 on the VAS (VAS 0.08 +/-0.3). Five patients reported changes in swallowing, and their VAS scores were 0.5, 0.9, 1.0, 2.7, and 6.9 (mean VAS 2.4+/-2.7). Forty patients (95%) were satisfied with their results and would undergo the reconstruction again.

CONCLUSION

Surgical airway reconstruction for severe OSA is a highly effective treatment option base on the objective as well as the subjective assessment.

Can snoring induce or worsen obstructive sleep apnea?

Snoring and sleep apneas are breathing disorders intimately associated during sleep. Most snorers are 'simple' or 'nonapneic', as the prevalence of snoring is much higher than that of sleep apneas. The vibrations transmitted to the pharyngeal structures by snoring span a large range of frequencies, while the energy transmitted may reach high values. A deleterious effect of these vibrations can therefore be considered. In 1983 a group of investigators from Bologna described five cases of heavy snorers of increasing severity, suggesting that they correspond to the natural history of 'heavy snorers' disease'. The present article reviews the data published since 1983 in favor of this hypothesis: anatomic lesions of the upper airway mucosa, pharyngeal muscles and nerves, and clinical observations in snorers. The conclusion stresses the absence of ultimate proof in favor of this attractive hypothesis: we lack the demonstration of a significant increase of the incidence of sleep apnea in a group of nonapneic snorers in a longitudinal follow-up study.

Acoustic analysis of vowel emission in obstructive sleep apnea

We studied vocalization in 18 men with obstructive sleep apnea syndrome (OSAS) (age, 49 [7.5] years; body mass index [BMI] 33.6 [7.6]) and 10 normal men as a control group (age, 46.7 [6.2] years; BMI 24.6 [2.2]). Polysomnographic data for patients with OSAS were as follows: total sleep time (TST), 387.5 [27.9] min; awake, 17.6 (12.6% TST); stage 1, 19.8 (18.7 percent TST); stage 2, 54.8 (23.2 percent TST); stage 3 and 4, 1.5 (0.3 percent TST); and stage REM, 4.2 (1.7 percent TST). Apnea hypopnea index (AHI) was 43.0 (18.2) and lowest O2 saturation was 73.6 (11.4). We recorded the following sounds in all subjects: /a/ as in "father"; /e/ as in "get"; /i/ as in "see"; /o/ as in "go"; /u/ as in "too." Three maneuvers for each vowel sound were taken for analysis. Signals were digitized at 10,000 Hz. Fast Fourier transformation was applied to segments of 512 points of each utterance corresponding to the vowel sound. The following parameters were obtained: maximum frequency of harmonics, mean frequency of harmonics, and the number of harmonics.

RESULTS

There were significant differences between both groups in the maximum frequency of harmonics of /i/ and /e/ vowels. (For /i/: 2,650 [672] Hz controls; 425 [71.2] Hz OSAS. For /e/: 2,605 [772.3] Hz controls; 1,250.0 [828.4] OSAS). The number of harmonics for /i/ vowel was 4.5 (1.2) for controls as compared with 2.7 (1) Hz for OSAS.

CONCLUSIONS

Vocalization in patients with OSAS is different from normal subjects. Vowel /i/ can distinguish these patients from normal subjects.

Speech changes following uvulopalatopharyngoplasty

Velopharyngeal function, voice and speech changes following uvulopalatopharyngoplasty (UPPP) were studied prospectively and compared with those in an age and sex matched group undergoing tonsillectomy. The fundamental frequency of voice was significantly lower in those undergoing UPPP. All the other changes studied were not significantly different in the two groups.

Speech status following uvulopalatopharyngoplasty

The purpose of this study was to evaluate the adequacy of speech following uvulopalatopharyngoplasty surgery. Twenty UPPP subjects, all of whom exhibited obstructive sleep apnea syndrome, and 15 non-UPPP control subjects participated in the study. Evaluation included measures of nasal airflow, speech recordings with listener judgments, and a questionnaire survey. Nasal resonance in the UPPP subjects was found not to be deviant by a panel of four experienced judges. The UPPP subjects were differentiated from their non-UPPP pairs on the basis of significant phonation (voice) problems, and to a lesser extent, their articulation problems. It is suggested that dryness problems that remained in many subjects postoperatively may be related to the observed voice problems.

Speech dysfunction of obstructive sleep apnea. A discriminant analysis of its descriptors

We have previously demonstrated a relationship between abnormal speech and obstructive sleep apnea in a small subject sample. The present study was designed to replicate the previous one with a much larger population, analyze the perceptual characteristics of the speech quality, and determine the degree to which each of three descriptors of speech abnormality contributed to the perception of speech abnormality. Ten graduate students in speech pathology listened in two 1.5 hour sessions to 252 random speech samples presented on a master tape. There were 81 subjects comprised of 27 sleep apnea patients, 27 matched chronic obstructive pulmonary disease control patients, and 27 matched normal control subjects. Rating the speech along an equally-appearing interval scale from 1 to 7, the judges heard abnormal resonance, articulation or phonation in 74 percent of the sleep apnea subjects, 53 percent of the COPD subjects, and 7 percent of the normal subjects (significant difference by chi 2 test at the .01 level of confidence). Discriminant function equations based on these speech descriptors correctly identified 96.3 percent of the normal subjects and 63.0 percent of the sleep apnea subjects. Analysis of abnormal speech resonance, articulation and phonation may identify obstructive sleep apnea or may provide insight into its pathology.