BACKGROUND: Developing L2 speaking proficiency can be challenging for learners, particularly when it comes to fostering self-regulation and maintaining engagement. Intelligent Personal Assistants (IPAs) offer a potential solution by providing accessible, interactive language learning opportunities.
METHODS: This mixed-methods study investigated the effectiveness of using Google Assistant within a learning-oriented feedback (LOA) framework to enhance L2 speaking proficiency, self-regulation, and learner engagement among 54 university-level EFL learners in China. Convenience sampling assigned participants to either an experimental group (n = 27) using Google Assistant with tailored activities or a control group (n = 27) using traditional methods. The Oral Proficiency Interview (OPI) assessed speaking performance. Self-reported questionnaires measured L2 motivation and the Scale of Strategic Self-Regulation for Speaking English as a Foreign Language (S2RS-EFL) evaluated speaking self-regulation. Additionally, semi-structured interviews with a subsample of the experimental group provided qualitative insights.
RESULTS: The Google Assistant group demonstrated a statistically significant improvement in speaking performance compared to the control group. While no significant difference in motivation was found, thematic analysis of interviews revealed perceived benefits of Google Assistant, including increased accessibility, interactivity, and immediate pronunciation feedback. These features likely contributed to a more engaging learning experience, potentially fostering self-regulation development in line with the core principles of LOA.
CONCLUSIONS: This study suggests Google Assistant as a promising supplementary tool for enhancing L2 speaking proficiency, learner autonomy, and potentially self-regulation within an LOA framework. Further research is needed to explore its impact on motivation and optimize engagement strategies.

Speech emotion recognition (SER) technology involves feature extraction and prediction models. However, recognition efficiency tends to decrease because of gender differences and the large number of extracted features. Consequently, this paper introduces a SER system based on gender. First, gender and emotion features are extracted from speech signals to develop gender recognition and emotion classification models. Second, according to gender differences, distinct emotion recognition models are established for male and female speakers. The gender of speakers is determined before executing the corresponding emotion model. Third, the accuracy of these emotion models is enhanced by utilizing an advanced differential evolution algorithm (ADE) to select optimal features. ADE incorporates new difference vectors, mutation operators, and position learning, which effectively balance global and local searches. A new position repairing method is proposed to address gender differences. Finally, experiments on four English datasets demonstrate that ADE is superior to comparison algorithms in recognition accuracy, recall, precision, F1-score, the number of used features and execution time. The findings highlight the significance of gender in refining emotion models, while mel-frequency cepstral coefficients are important factors in gender differences.

UNASSIGNED: This study aims to assess the potential efficacy of cochlear implantation as a treatment for patients with Waardenburg syndrome (WS) and to guide clinical work by comparing the effect of auditory and speech recovery after cochlear implantation in patients with WS and non-WS.
UNASSIGNED: PubMed, the Cochrane Library, CNKI, and Wanfang Data were sources for retrieving literature on cochlear implantation in WS, and clinical data meeting the inclusion criteria were meta-analyzed using RevMan5.41.
UNASSIGNED: A total of nine articles were included in this study, including 132 patients with WS and 815 patients in the control group. Meta-analysis showed that there are no significant differences in the scores for categories of audit performance (CAP), speech intelligibility rating (SIR), and parents\' evaluation of aural/oral performance of children (PEACH) between the WS group and the control group.
UNASSIGNED: Cochlear implantation demonstrates comparable auditory and speech recovery outcomes for WS patients and non-WS patients.

Abnormal speech prosody has been widely reported in individuals with autism. Many studies on children and adults with autism spectrum disorder speaking a non-tonal language showed deficits in using prosodic cues to mark focus. However, focus marking by autistic children speaking a tonal language is rarely examined. Cantonese-speaking children may face additional difficulties because tonal languages require them to use prosodic cues to achieve multiple functions simultaneously such as lexical contrasting and focus marking. This study bridges this research gap by acoustically evaluating the use of Cantonese speech prosody to mark information structure by Cantonese-speaking children with and without autism spectrum disorder. We designed speech production tasks to elicit natural broad and narrow focus production among these children in sentences with different tone combinations. Acoustic correlates of prosodic focus marking like f0, duration and intensity of each syllable were analyzed to examine the effect of participant group, focus condition and lexical tones. Our results showed differences in focus marking patterns between Cantonese-speaking children with and without autism spectrum disorder. The autistic children not only showed insufficient on-focus expansion in terms of f0 range and duration when marking focus, but also produced less distinctive tone shapes in general. There was no evidence that the prosodic complexity (i.e. sentences with single tones or combinations of tones) significantly affected focus marking in these autistic children and their typically-developing (TD) peers.

OBJECTIVE: This study aims to conduct a systematic review and meta-analysis of the diagnostic accuracy of deep learning (DL) using speech samples in depression.
METHODS: This review included studies reporting diagnostic results of DL algorithms in depression using speech data, published from inception to January 31, 2024, on PubMed, Medline, Embase, PsycINFO, Scopus, IEEE, and Web of Science databases. Pooled accuracy, sensitivity, and specificity were obtained by random-effect models. The diagnostic Precision Study Quality Assessment Tool (QUADAS-2) was used to assess the risk of bias.
RESULTS: A total of 25 studies met the inclusion criteria and 8 of them were used in the meta-analysis. The pooled estimates of accuracy, specificity, and sensitivity for depression detection models were 0.87 (95% CI, 0.81-0.93), 0.85 (95% CI, 0.78-0.91), and 0.82 (95% CI, 0.71-0.94), respectively. When stratified by model structure, the highest pooled diagnostic accuracy was 0.89 (95% CI, 0.81-0.97) in the handcrafted group.
CONCLUSIONS: To our knowledge, our study is the first meta-analysis on the diagnostic performance of DL for depression detection from speech samples. All studies included in the meta-analysis used convolutional neural network (CNN) models, posing problems in deciphering the performance of other DL algorithms. The handcrafted model performed better than the end-to-end model in speech depression detection.
CONCLUSIONS: The application of DL in speech provided a useful tool for depression detection. CNN models with handcrafted acoustic features could help to improve the diagnostic performance.
BACKGROUND: The study protocol was registered on PROSPERO (CRD42023423603).

Recent research has extensively reported the phenomenon of inter-brain neural coupling between speakers and listeners during speech communication. Yet, the specific speech processes underlying this neural coupling remain elusive. To bridge this gap, this study estimated the correlation between the temporal dynamics of speaker-listener neural coupling with speech features, utilizing two inter-brain datasets accounting for different noise levels and listener\'s language experiences (native vs. non-native). We first derived time-varying speaker-listener neural coupling, extracted acoustic feature (envelope) and semantic features (entropy and surprisal) from speech, and then explored their correlational relationship. Our findings reveal that in clear conditions, speaker-listener neural coupling correlates with semantic features. However, as noise increases, this correlation is only significant for native listeners. For non-native listeners, neural coupling correlates predominantly with acoustic feature rather than semantic features. These results revealed how speaker-listener neural coupling is associated with the acoustic and semantic features under various scenarios, enriching our understanding of the inter-brain neural mechanisms during natural speech communication. We therefore advocate for more attention on the dynamic nature of speaker-listener neural coupling and its modeling with multilevel speech features.

OBJECTIVE: Loneliness impacts the health of many older adults, yet effective and targeted interventions are lacking. Compared to surveys, speech data can capture the personalized experience of loneliness. In this proof-of-concept study, we used Natural Language Processing to extract novel linguistic features and AI approaches to identify linguistic features that distinguish lonely adults from non-lonely adults.
METHODS: Participants completed UCLA loneliness scales and semi-structured interviews (sections: social relationships, loneliness, successful aging, meaning/purpose in life, wisdom, technology and successful aging). We used the Linguistic Inquiry and Word Count (LIWC-22) program to analyze linguistic features and built a classifier to predict loneliness. Each interview section was analyzed using an explainable AI (XAI) model to classify loneliness.
RESULTS: The sample included 97 older adults (age 66-101 years, 65 % women). The model had high accuracy (Accuracy: 0.889, AUC: 0.8), precision (F1: 0.8), and recall (1.0). The sections on social relationships and loneliness were most important for classifying loneliness. Social themes, conversational fillers, and pronoun usage were important features for classifying loneliness.
CONCLUSIONS: XAI approaches can be used to detect loneliness through the analyses of unstructured speech and to better understand the experience of loneliness.

Considerable work has investigated similarities between the processing of music and language, but it remains unclear whether typical, genuine music can influence speech processing via cross-domain priming. To investigate this, we measured ERPs to musical phrases and to syntactically ambiguous Chinese phrases that could be disambiguated by early or late prosodic boundaries. Musical primes also had either early or late prosodic boundaries and we asked participants to judge whether the prime and target have the same structure. Within musical phrases, prosodic boundaries elicited reduced N1 and enhanced P2 components (relative to the no-boundary condition) and musical phrases with late boundaries exhibited a closure positive shift (CPS) component. More importantly, primed target phrases elicited a smaller CPS compared to non-primed phrases, regardless of the type of ambiguous phrase. These results suggest that prosodic priming can occur across domains, supporting the existence of common neural processes in music and language processing.

Existing end-to-end speech recognition methods typically employ hybrid decoders based on CTC and Transformer. However, the issue of error accumulation in these hybrid decoders hinders further improvements in accuracy. Additionally, most existing models are built upon Transformer architecture, which tends to be complex and unfriendly to small datasets. Hence, we propose a Nonlinear Regularization Decoding Method for Speech Recognition. Firstly, we introduce the nonlinear Transformer decoder, breaking away from traditional left-to-right or right-to-left decoding orders and enabling associations between any characters, mitigating the limitations of Transformer architectures on small datasets. Secondly, we propose a novel regularization attention module to optimize the attention score matrix, reducing the impact of early errors on later outputs. Finally, we introduce the tiny model to address the challenge of overly large model parameters. The experimental results indicate that our model demonstrates good performance. Compared to the baseline, our model achieves recognition improvements of 0.12%, 0.54%, 0.51%, and 1.2% on the Aishell1, Primewords, Free ST Chinese Corpus, and Common Voice 16.1 datasets of Uyghur, respectively.

Lip language recognition urgently needs wearable and easy-to-use interfaces for interference-free and high-fidelity lip-reading acquisition and to develop accompanying data-efficient decoder-modeling methods. Existing solutions suffer from unreliable lip reading, are data hungry, and exhibit poor generalization. Here, we propose a wearable lip language decoding technology that enables interference-free and high-fidelity acquisition of lip movements and data-efficient recognition of fluent lip language based on wearable motion capture and continuous lip speech movement reconstruction. The method allows us to artificially generate any wanted continuous speech datasets from a very limited corpus of word samples from users. By using these artificial datasets to train the decoder, we achieve an average accuracy of 92.0% across individuals (n = 7) for actual continuous and fluent lip speech recognition for 93 English sentences, even observing no training burn on users because all training datasets are artificially generated. Our method greatly minimizes users\' training/learning load and presents a data-efficient and easy-to-use paradigm for lip language recognition.