Search for: All records

Acoustic analysis of typically developing elementary school-aged (prepubertal) children’s speech has been primarily performed on cross-sectional data in the past. Few studies have examined longitudinal data in this age group. For this presentation, we analyze the developmental changes in the acoustic properties of children’s speech using data collected longitudinally over four years (from first grade to fourth grade). Four male and four female children participated in this study. Data were collected once every year for each child. Using these data, we measured the four-year development of subglottal acoustics (first two subglottal resonances) and vowel acoustics (first four formants and fundamental frequency). Subglottal acoustic measurements are relatively independent of context, and average values were obtained for each child in each year. Vowel acoustics measurements were made for seven vowels (i, ɪ, ɛ, æ, ʌ, ɑ, u), each occurring in two different words in the stressed syllable. We investigated the correlations between the children’s subglottal acoustics, vowel acoustics, and growth-related variables such as standing height, sitting height, and chronological age. Gender-, vowel-, and child-specific analyses were carried out in order to shed light on how typically developing speech acoustics depend on such variables. [Work supported, in part, by the NSF.]

Children’s automatic speech recognition (ASR) is always difficult due to, in part, the data scarcity problem, especially for kindergarten-aged kids. When data are scarce, the model might overfit to the training data, and hence good starting points for training are essential. Recently, meta-learning was proposed to learn model initialization (MI) for ASR tasks of different languages. This method leads to good performance when the model is adapted to an unseen language. How-ever, MI is vulnerable to overfitting on training tasks (learner overfitting). It is also unknown whether MI generalizes to other low-resource tasks. In this paper, we validate the effectiveness of MI in children’s ASR and attempt to alleviate the problem of learner overfitting. To achieve model-agnostic meta-learning (MAML), we regard children’s speech at each age as a different task. In terms of learner overfitting, we propose a task-level augmentation method by simulating new ages using frequency warping techniques. Detailed experiments are conducted to show the impact of task augmentation on each age for kindergarten-aged speech. As a result, our approach achieves a relative word error rate (WER) improvement of 51% over the baseline system with no augmentation or initialization.

This paper proposes a novel linear prediction coding-based data augmentation method for children’s low and zero resource dialect ASR. The data augmentation procedure consists of perturbing the formant peaks of the LPC spectrum during LPC analysis and reconstruction. The method is evaluated on two novel children’s speech datasets with one containing California English from the Southern California Area and the other containing a mix of Southern American English and African American English from the Atlanta, Georgia area. We test the proposed method in training both an HMM-DNN system and an end-to-end system to show model-robustness and demonstrate that the algorithm improves ASR performance, especially for zero resource dialect children’s task, as compared to common data augmentation methods such as VTLP, Speed Perturbation, and SpecAugment.

This paper presents the results of a pilot study that introduces social robots into kindergarten and first-grade classroom tasks. This study aims to understand 1) how effective social robots are in administering educational activities and assessments, and 2) if these interactions with social robots can serve as a gateway into learning about robotics and STEM for young children. We administered a commonly-used assessment (GFTA3) of speech production using a social robot and compared the quality of recorded responses to those obtained with a human assessor. In a comparison done between 40 children, we found no significant differences in the student responses between the two conditions over the three metrics used: word repetition accuracy, number of times additional help was needed, and similarity of prosody to the assessor. We also found that interactions with the robot were successfully able to stimulate curiosity in robotics, and therefore STEM, from a large number of the 164 student participants.