Heng Yin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Heng Yin has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Bing Shi
State Key Laboratory of Oral Diseases and National Clinical Research Center for Oral Diseases, and Department of Oral and Maxillofacial Surgery, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, 610041, China
3 shared publications- Jing Zhang
Sichuan University
3 shared publications - Jingtao Li
Sichuan University
3 shared publications Li Yang
State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, Dept. of Cleft Lip and Palate Surgery, West China Hospital of Stomatology, Sichuan University, Chengdu 610041, China
3 shared publications- Ling He
Sichuan University
3 shared publications Shi Bing
State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, Dept. of Cleft Lip and Palate Surgery, West China Hospital of Stomatology, Sichuan University, Chengdu 610041, China
3 shared publications
Latest Publications
- Open Access
- 21 August 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (16) , 2714
Automatic Detection System for Velopharyngeal Insufficiency Based on Acoustic Signals from Nasal and Oral Channels
Velopharyngeal insufficiency (VPI) is a type of pharyngeal function dysfunction that causes speech impairment and swallowing disorder. Speech therapists play a key role on the diagnosis and treatment of speech disorders. However, there is a worldwide shortage of experienced speech therapists. Artificial intelligence-based computer-aided diagnosing technology could be a solution for this. This paper proposes an automatic system for VPI detection at the subject level. It is a non-invasive and convenient approach for VPI diagnosis. Based on the principle of impaired articulation of VPI patients, nasal- and oral-channel acoustic signals are collected as raw data. The system integrates the symptom discriminant results at the phoneme level. For consonants, relative prominent frequency description and relative frequency distribution features are proposed to discriminate nasal air emission caused by VPI. For hypernasality-sensitive vowels, a cross-attention residual Siamese network (CARS-Net) is proposed to perform automatic VPI/non-VPI classification at the phoneme level. CARS-Net embeds a cross-attention module between the two branches to improve the VPI/non-VPI classification model for vowels. We validate the proposed system on a self-built dataset, and the accuracy reaches 98.52%. This provides possibilities for implementing automatic VPI diagnosis.
- 21 August 2023
- Published by MDPI AG in Diagnostics
- Vol. 13 (16) , 2714
Open AccessAutomatic Detection System for Velopharyngeal Insufficiency Based on Acoustic Signals from Nasal and Oral Channels
Velopharyngeal insufficiency (VPI) is a type of pharyngeal function dysfunction that causes speech impairment and swallowing disorder. Speech therapists play a key role on the diagnosis and treatment of speech disorders. However, there is a worldwide shortage of experienced speech therapists. Artificial intelligence-based computer-aided diagnosing technology could be a solution for this. This paper proposes an automatic system for VPI detection at the subject level. It is a non-invasive and convenient approach for VPI diagnosis. Based on the principle of impaired articulation of VPI patients, nasal- and oral-channel acoustic signals are collected as raw data. The system integrates the symptom discriminant results at the phoneme level. For consonants, relative prominent frequency description and relative frequency distribution features are proposed to discriminate nasal air emission caused by VPI. For hypernasality-sensitive vowels, a cross-attention residual Siamese network (CARS-Net) is proposed to perform automatic VPI/non-VPI classification at the phoneme level. CARS-Net embeds a cross-attention module between the two branches to improve the VPI/non-VPI classification model for vowels. We validate the proposed system on a self-built dataset, and the accuracy reaches 98.52%. This provides possibilities for implementing automatic VPI diagnosis.
- 10 June 2023
- Published by Elsevier in International Journal of Pediatric Otorhinolaryngology
- Vol. 171, 111607
Development of postoperative velopharyngeal function in patients with cleft palate
- 10 June 2023
- Published by Elsevier in International Journal of Pediatric Otorhinolaryngology
- Vol. 171, 111607
Development of postoperative velopharyngeal function in patients with cleft palate
- 1 February 2020
- Vol. 38 (1) , 48-53
[Changes of postoperative velopharyngeal function in children with cleft palate under 5 years old].
To demonstrate the regularity of velopharyngeal function recovery after primary cleft palatoplasty and its correlation with different surgical procedures, ages, cleft types, and follow-up times. Patients with cleft palate under 5 years old who had more than two follow-up records were included in this study, and consecutive evaluations of postoperative velopharyngeal function were performed. Univariate and multivariate logistic regression analysis were used to reveal the regularity of postoperative velopharyngeal function and the possible influencing factors. A total of 165 patients were included. Inconsistent functions of the velopharyngeal closure were observed in 31 patients, of which velopharyngeal insufficiency (VPI) in the first follow-up converted to velopharyngeal competence (VPC) in the second follow-up, accounting for 18.79% of the total, and 134 patients had consistent velopharyngeal function. The patients in the group who had consistent velopharyngeal function were younger than those in the group who were inconsistent, and the differences between the two groups were statistically significant. The younger the operation age, the patient's velopharyngeal function was more likely to stabilize at the first follow-up. At the time of the first follow-up in 15, 28, and 40 months, the probability that the patients had stable postoperative velopharyngeal function was 80%, 90%, and 95%, respectively. The recovery of velopharyn-geal function after surgery is a dynamic process. The velopharyngeal status of patients can be converted from VPI to VPC. Meanwhile, VPC cannot switch to VPI. The follow-up time is the most important factor affecting the consistency of the evaluation of velopharyngeal function. Choosing appro-priate follow-up time is the key to obtain the stable evaluation of velopharyngeal function.
- 1 February 2020
- Vol. 38 (1) , 48-53
[Changes of postoperative velopharyngeal function in children with cleft palate under 5 years old].
To demonstrate the regularity of velopharyngeal function recovery after primary cleft palatoplasty and its correlation with different surgical procedures, ages, cleft types, and follow-up times. Patients with cleft palate under 5 years old who had more than two follow-up records were included in this study, and consecutive evaluations of postoperative velopharyngeal function were performed. Univariate and multivariate logistic regression analysis were used to reveal the regularity of postoperative velopharyngeal function and the possible influencing factors. A total of 165 patients were included. Inconsistent functions of the velopharyngeal closure were observed in 31 patients, of which velopharyngeal insufficiency (VPI) in the first follow-up converted to velopharyngeal competence (VPC) in the second follow-up, accounting for 18.79% of the total, and 134 patients had consistent velopharyngeal function. The patients in the group who had consistent velopharyngeal function were younger than those in the group who were inconsistent, and the differences between the two groups were statistically significant. The younger the operation age, the patient's velopharyngeal function was more likely to stabilize at the first follow-up. At the time of the first follow-up in 15, 28, and 40 months, the probability that the patients had stable postoperative velopharyngeal function was 80%, 90%, and 95%, respectively. The recovery of velopharyn-geal function after surgery is a dynamic process. The velopharyngeal status of patients can be converted from VPI to VPC. Meanwhile, VPC cannot switch to VPI. The follow-up time is the most important factor affecting the consistency of the evaluation of velopharyngeal function. Choosing appro-priate follow-up time is the key to obtain the stable evaluation of velopharyngeal function.
- 3 December 2018
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 22 (1) , 59-65
Automatic detection of consonant omission in cleft palate speech
- 3 December 2018
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 22 (1) , 59-65
Automatic detection of consonant omission in cleft palate speech
- 1 April 2018
- Vol. 36 (2) , 146-149
[Outcome and influential factors of speech therapy delivered to cleft patients with post-operative velopharyngeal competence].
To analyze the training technique, intervention timing, and other related factors involved in the speech therapy delivered to cleft patients with velopharyngeal competence after surgery. A retrospective study was conducted on 32 patients who received phonology-articulation speech therapies during 2012 to 2013 in Dept. of Cleft Lip and Palate, West China Hospital of Stomatology, Sichuan University. All patients achieved normal speech one year after therapy. Information collected included the types and number of consonant articulation error, the overall period of training, the interval between surgery and speech training, and the age during speech training. Statistical analyses were performed in SPSS 16.0. Ten patients received less than five sessions of training, seventeen received six to ten sessions, and five received eleven to twenty sessions. The number of sessions was positively correlated with the number of errors (r(s)=0.394, P=0.026). On the average, each additional error cost another 0.570 session for correction (confidence interval: 0.137-1.004). Moreover, the number of sessions was negatively correlated with age (P=0.055). Patients between 5 to 10 years old took significantly lesser sessions than those above 10 years. No correlation was found between the number of sessions and the interval between surgeries and trainings. Appropriate speech therapy efficiently rehabilitate the speech condition of cleft patients with velopharyngeal sufficiency after surgery. The number of errors is directly proportional to the number of sessions needed. Patients above 10 years require more sessions than those less than 10 years.
- 1 April 2018
- Vol. 36 (2) , 146-149
[Outcome and influential factors of speech therapy delivered to cleft patients with post-operative velopharyngeal competence].
To analyze the training technique, intervention timing, and other related factors involved in the speech therapy delivered to cleft patients with velopharyngeal competence after surgery. A retrospective study was conducted on 32 patients who received phonology-articulation speech therapies during 2012 to 2013 in Dept. of Cleft Lip and Palate, West China Hospital of Stomatology, Sichuan University. All patients achieved normal speech one year after therapy. Information collected included the types and number of consonant articulation error, the overall period of training, the interval between surgery and speech training, and the age during speech training. Statistical analyses were performed in SPSS 16.0. Ten patients received less than five sessions of training, seventeen received six to ten sessions, and five received eleven to twenty sessions. The number of sessions was positively correlated with the number of errors (r(s)=0.394, P=0.026). On the average, each additional error cost another 0.570 session for correction (confidence interval: 0.137-1.004). Moreover, the number of sessions was negatively correlated with age (P=0.055). Patients between 5 to 10 years old took significantly lesser sessions than those above 10 years. No correlation was found between the number of sessions and the interval between surgeries and trainings. Appropriate speech therapy efficiently rehabilitate the speech condition of cleft patients with velopharyngeal sufficiency after surgery. The number of errors is directly proportional to the number of sessions needed. Patients above 10 years require more sessions than those less than 10 years.
- 1 June 2017
- Vol. 35 (3) , 296-300
[Velopharyngeal closure pattern and speech performance among submucous cleft palate patients].
To characterize the velopharyngeal closure patterns and speech performance among submucous cleft palate patients. Patients with submucous cleft palate visiting the Department of Cleft Lip and Palate Surgery, West China Hospital of Stomatology, Sichuan University between 2008 and 2016 were reviewed. Outcomes of subjective speech evaluation including velopharyngeal function, consonant articulation, and objective nasopharyngeal endoscopy including the mobility of soft palate, pharyngeal walls were retrospectively analyzed. A total of 353 cases were retrieved in this study, among which 138 (39.09%) demonstrated velopharyngeal competence, 176 (49.86%) velopharyngeal incompetence, and 39 (11.05%) marginal velopharyngeal incompetence. A total of 268 cases were subjected to nasopharyngeal endoscopy examination, where 167 (62.31%) demonstrated circular closure pattern, 89 (33.21%) coronal pattern, and 12 (4.48%) sagittal pattern. Passavant's ridge existed in 45.51% (76/167) patients with circular closure and 13.48% (12/89) patients with coronal closure. Among the 353 patients included in this study, 137 (38.81%) presented normal articulation, 124 (35.13%) consonant elimination, 51 (14.45%) compensatory articulation, 36 (10.20%) consonant weakening, 25 (7.08%) consonant replacement, and 36 (10.20%) multiple articulation errors. Circular closure was the most prevalent velopharyngeal closure pattern among patients with submucous cleft palate, and high-pressure consonant deletion was the most common articulation abnormality. Articulation error occurred more frequently among patients with a low velopharyngeal closure rate.
- 1 June 2017
- Vol. 35 (3) , 296-300
[Velopharyngeal closure pattern and speech performance among submucous cleft palate patients].
To characterize the velopharyngeal closure patterns and speech performance among submucous cleft palate patients. Patients with submucous cleft palate visiting the Department of Cleft Lip and Palate Surgery, West China Hospital of Stomatology, Sichuan University between 2008 and 2016 were reviewed. Outcomes of subjective speech evaluation including velopharyngeal function, consonant articulation, and objective nasopharyngeal endoscopy including the mobility of soft palate, pharyngeal walls were retrospectively analyzed. A total of 353 cases were retrieved in this study, among which 138 (39.09%) demonstrated velopharyngeal competence, 176 (49.86%) velopharyngeal incompetence, and 39 (11.05%) marginal velopharyngeal incompetence. A total of 268 cases were subjected to nasopharyngeal endoscopy examination, where 167 (62.31%) demonstrated circular closure pattern, 89 (33.21%) coronal pattern, and 12 (4.48%) sagittal pattern. Passavant's ridge existed in 45.51% (76/167) patients with circular closure and 13.48% (12/89) patients with coronal closure. Among the 353 patients included in this study, 137 (38.81%) presented normal articulation, 124 (35.13%) consonant elimination, 51 (14.45%) compensatory articulation, 36 (10.20%) consonant weakening, 25 (7.08%) consonant replacement, and 36 (10.20%) multiple articulation errors. Circular closure was the most prevalent velopharyngeal closure pattern among patients with submucous cleft palate, and high-pressure consonant deletion was the most common articulation abnormality. Articulation error occurred more frequently among patients with a low velopharyngeal closure rate.
- 1 October 2016
- Vol. 34 (5) , 488-492
[Morphological classification and velopharyngeal function analysis of submucous cleft palate patients].
To enhance the accuracy in diagnosis and management of submucous cleft palate via a thorough analysis of its anatomical and functional details. Two hundred seventy-six submucous cleft palate cases from 2008 to 2014 were retrospectively investigated. Subgroup analysis were performed on the basis of preoperative velopharyngeal function, palatal morphology, cleft lip concurrence, and patient motives for treatment. Among the included cases, 96 (34.78%) were presented as velopharyngeal competence (VPC), 151 (54.71%) as velopharyngeal insufficiency (VPI), and 29 (10.51%) as marginal VPI (MVPI). Eighty cases (28.99%) also demonstrated cleft lip deformity, and 196 cases (71.01%) were merely submucous cleft palate. Compared with patients with submucous cleft palate only, those with cleft lips exhibited higher rates of complete velopharyngeal closure. The pathological spectrum of submucous cleft palate varied significantly. Only 103 (37.32%) cases met all the three diagnostic criteria proposed by Calnan. Given that the velopharyngeal closure rate varies among the subgroups, the factors analyzed in this study should be considered in the personalized manage-ment of submucous cleft palate.
- 1 October 2016
- Vol. 34 (5) , 488-492
[Morphological classification and velopharyngeal function analysis of submucous cleft palate patients].
To enhance the accuracy in diagnosis and management of submucous cleft palate via a thorough analysis of its anatomical and functional details. Two hundred seventy-six submucous cleft palate cases from 2008 to 2014 were retrospectively investigated. Subgroup analysis were performed on the basis of preoperative velopharyngeal function, palatal morphology, cleft lip concurrence, and patient motives for treatment. Among the included cases, 96 (34.78%) were presented as velopharyngeal competence (VPC), 151 (54.71%) as velopharyngeal insufficiency (VPI), and 29 (10.51%) as marginal VPI (MVPI). Eighty cases (28.99%) also demonstrated cleft lip deformity, and 196 cases (71.01%) were merely submucous cleft palate. Compared with patients with submucous cleft palate only, those with cleft lips exhibited higher rates of complete velopharyngeal closure. The pathological spectrum of submucous cleft palate varied significantly. Only 103 (37.32%) cases met all the three diagnostic criteria proposed by Calnan. Given that the velopharyngeal closure rate varies among the subgroups, the factors analyzed in this study should be considered in the personalized manage-ment of submucous cleft palate.
- 28 March 2015
- Published by Springer Nature in Journal of Medical Systems
- Vol. 39 (5) , 1-7
Automatic Evaluation of Hypernasality Based on a Cleft Palate Speech Database
The hypernasality is one of the most typical characteristics of cleft palate (CP) speech. The evaluation outcome of hypernasality grading decides the necessity of follow-up surgery. Currently, the evaluation of CP speech is carried out by experienced speech therapists. However, the result strongly depends on their clinical experience and subjective judgment. This work aims to propose an automatic evaluation system for hypernasality grading in CP speech. The database tested in this work is collected by the Hospital of Stomatology, Sichuan University, which has the largest number of CP patients in China. Based on the production process of hypernasality, source sound pulse and vocal tract filter features are presented. These features include pitch, the first and second energy amplified frequency bands, cepstrum based features, MFCC, short-time energy in the sub-bands features. These features combined with KNN classier are applied to automatically classify four grades of hypernasality: normal, mild, moderate and severe. The experiment results show that the proposed system achieves a good performance. The classification rates for four hypernasality grades reach up to 80.4 %. The sensitivity of proposed features to the gender is also discussed.
- 28 March 2015
- Published by Springer Nature in Journal of Medical Systems
- Vol. 39 (5) , 1-7
Automatic Evaluation of Hypernasality Based on a Cleft Palate Speech Database
The hypernasality is one of the most typical characteristics of cleft palate (CP) speech. The evaluation outcome of hypernasality grading decides the necessity of follow-up surgery. Currently, the evaluation of CP speech is carried out by experienced speech therapists. However, the result strongly depends on their clinical experience and subjective judgment. This work aims to propose an automatic evaluation system for hypernasality grading in CP speech. The database tested in this work is collected by the Hospital of Stomatology, Sichuan University, which has the largest number of CP patients in China. Based on the production process of hypernasality, source sound pulse and vocal tract filter features are presented. These features include pitch, the first and second energy amplified frequency bands, cepstrum based features, MFCC, short-time energy in the sub-bands features. These features combined with KNN classier are applied to automatically classify four grades of hypernasality: normal, mild, moderate and severe. The experiment results show that the proposed system achieves a good performance. The classification rates for four hypernasality grades reach up to 80.4 %. The sensitivity of proposed features to the gender is also discussed.
- 1 October 2014
- Vol. 32 (5) , 432-5
[Correlative factors on the articulation disorder of patients with cleft palate].
To investigate the correlation between articulation, velopharyngeal function, and surgical age by comparing the changes in articulation after velopharyngeal closure is performed. This study is also conducted to investigate the influencing factors of omission change between pre- and post-operation. A total of 48 patients, including 18 males and 30 females, mean age (13.3 ± 5.8) years, with non-syndromic cleft lips and palates were selected from January 2011 to December 2011. Their speech data and articulation between pre- and post-operation were retrospectively analyzed using non-parametric tests. Correlation study was performed to analyze the influencing factors of the changes in articulation. P < 0.05 was considered statistically significant. The difference in articulation after velopharyngeal closure occurred was significant (Z = -3.796, P = 0.000). A negative correlation between the ratio of post-operative normal articulation and surgical age (R = -0.487, P = 0.000) was observed. The change in omission was positively correlated with surgical age (R = 0.589, P = 0.000) and gender (R = 0.404, P = 0.047). By comparison, the change in omission was negatively correlated with follow-up time (R = -0.235, P = 0.040). Articulation and intelligibility are significantly improved after velopharyngeal closure is performed. These parameters are negatively correlated with surgical age to some extent. In addition, the change in omission is positively correlated with surgical age and gender, whereas the change in omission is negatively correlated with follow-up time.
- 1 October 2014
- Vol. 32 (5) , 432-5
[Correlative factors on the articulation disorder of patients with cleft palate].
To investigate the correlation between articulation, velopharyngeal function, and surgical age by comparing the changes in articulation after velopharyngeal closure is performed. This study is also conducted to investigate the influencing factors of omission change between pre- and post-operation. A total of 48 patients, including 18 males and 30 females, mean age (13.3 ± 5.8) years, with non-syndromic cleft lips and palates were selected from January 2011 to December 2011. Their speech data and articulation between pre- and post-operation were retrospectively analyzed using non-parametric tests. Correlation study was performed to analyze the influencing factors of the changes in articulation. P < 0.05 was considered statistically significant. The difference in articulation after velopharyngeal closure occurred was significant (Z = -3.796, P = 0.000). A negative correlation between the ratio of post-operative normal articulation and surgical age (R = -0.487, P = 0.000) was observed. The change in omission was positively correlated with surgical age (R = 0.589, P = 0.000) and gender (R = 0.404, P = 0.047). By comparison, the change in omission was negatively correlated with follow-up time (R = -0.235, P = 0.040). Articulation and intelligibility are significantly improved after velopharyngeal closure is performed. These parameters are negatively correlated with surgical age to some extent. In addition, the change in omission is positively correlated with surgical age and gender, whereas the change in omission is negatively correlated with follow-up time.