Second Life is a multi-user virtual world platform which enables online learning through immersive activities. This study evaluates the perception of third-year biomedical engineering students about learning activities complementary to a biomedical imaging course carried out within Second Life and focused on training in the public presentation of scientific content to their peers. Between 2015 and 2017, students gave oral presentations on medical imaging topics selected from the proposals of their classmates. Participants were invited to complete an evaluation questionnaire. In the three years of the study, 133 students enrolled in the course (48, 46, and 39 consecutively), and 97 of them delivered the questionnaire (48%, 83%, and 92%, consecutively). Attendance at the sessions ranged between 88% and 44%. The students positively value the experiences, especially the teacher, the educational content, and the virtual island environment, with mean scores greater than or equal to 8.4, 7.7, and 7.7, respectively, on a 1–10-point scale. Overall, they valued Second Life as an attractive and suitable environment for their training in science communication skills, in which they gain self-confidence and are less afraid of speaking in public. Second Life enables students to present scientific content effectively to their peers, receiving hands-on training in the tasks of collecting, organizing, and presenting data, with the benefits of remote access, collaborative work, and social interaction.

Automatic tools to detect hypernasality have been traditionally designed to analyze sustained vowels exclusively. This is in sharp contrast with clinical recommendations, which consider it necessary to use a variety of utterance types (e.g., repeated syllables, sustained sounds, sentences, etc.) This study explores the feasibility of detecting hypernasality automatically based on speech samples other than sustained vowels. The participants were 39 patients and 39 healthy controls. Six types of utterances were used: counting 1-to-10 and repetition of syllable sequences, sustained consonants, sustained vowel, words and sentences. The recordings were obtained, with the help of a mobile app, from Spain, Chile and Ecuador. Multiple acoustic features were computed from each utterance (e.g., MFCC, formant frequency) After a selection process, the best 20 features served to train different classification algorithms. Accuracy was the highest with syllable sequences and also with some words and sentences. Accuracy increased slightly by training the classifiers with between two and three utterances. However, the best results were obtained by combining the results of multiple classifiers. We conclude that protocols for automatic evaluation of hypernasality should include a variety of utterance types. It seems feasible to detect hypernasality automatically with mobile devices.

Nasalance is a valuable clinical biomarker for hypernasality. It is computed as the ratio of acoustic energy emitted through the nose to the total energy emitted through the mouth and nose (eNasalance). A new approach is proposed to compute nasalance using Convolutional Neural Networks (CNNs) trained with Mel-Frequency Cepstrum Coefficients (mfccNasalance). mfccNasalance is evaluated by examining its accuracy: 1) when the train and test data are from the same or from different dialects; 2) with test data that differs in dynamicity (e.g. rapidly produced diadochokinetic syllables versus short words); and 3) using multiple CNN configurations (i.e. kernel shape and use of 1 × 1 pointwise convolution). Dual-channel Nasometer speech data from healthy speakers from different dialects: Costa Rica, more(+) nasal, Spain and Chile, less(-) nasal, are recorded. The input to the CNN models were sequences of 39 MFCC vectors computed from 250 ms moving windows. The test data were recorded in Spain and included short words (-dynamic), sentences (+dynamic), and diadochokinetic syllables (+dynamic). The accuracy of a CNN model was defined as the Spearman correlation between the mfccNasalance for that model and the perceptual nasality scores of human experts. In the same-dialect condition, mfccNasalance was more accurate than eNasalance independently of the CNN configuration; using a 1 × 1 kernel resulted in increased accuracy for +dynamic utterances (p < .000), though not for -dynamic utterances. The kernel shape had a significant impact for -dynamic utterances (p < .000) exclusively. In the different-dialect condition, the scores were significantly less accurate than in the same-dialect condition, particularly for Costa Rica trained models. We conclude that mfccNasalance is a flexible and useful alternative to eNasalance. Future studies should explore how to optimize mfccNasalance by selecting the most adequate CNN model as a function of the dynamicity of the target speech data.

Automatic evaluation of hypernasality has been traditionally computed using monophonic signals (i.e., combining nose and mouth signals). Here, this study aimed to examine if nose signals serve to increase the accuracy of hypernasality evaluation. Using a conventional microphone and a Nasometer, we recorded monophonic, mouth, and nose signals. Three main analyses were performed: (1) comparing the spectral distance between oral/nasalized vowels in monophonic, nose, and mouth signals; (2) assessing the accuracy of Deep Neural Network (DNN) models in classifying oral/nasal sounds and vowel/consonant sounds trained with nose, mouth, and monophonic signals; (3) analyzing the correlation between DNN-derived nasality scores and expert-rated hypernasality scores. The distance between oral and nasalized vowels was the highest in the nose signals. Moreover, DNN models trained on nose signals outperformed in nasal/oral classification (accuracy: 0.90), but were slightly less precise in vowel/consonant differentiation (accuracy: 0.86) compared to models trained on other signals. A strong Pearson’s correlation (0.83) was observed between nasality scores from DNNs trained with nose signals and human expert ratings, whereas those trained on mouth signals showed a weaker correlation (0.36). We conclude that mouth signals partially mask the nasality information carried by nose signals. Significance: the accuracy of hypernasality assessment tools may improve by analyzing nose signals.