arXiv subjects

João Lima

Publications and source records attributed to João Lima.

6 recordsLinked to original sources

arXiv2026

Automated Assessment of L2 Speech Rhythm Using Low-Frequency Amplitude Modulations

Automated Speaking Assessment of non-native speech must effectively evaluate prosody, including speech rhythm, to align with human perception. However, commonly employed rhythm metrics rely on segmental duration, requiring an additional alignment step, which is error-prone in non-native speech containing disfluencies and mispronunciations. We propose an acoustics-based assessment approach that employs a convolutional neural network to extract rhythm features directly from the speech amplitude envelope, motivated by evidence linking low-frequency modulations to rhythm perception. The proposed models are trained on a proficiency score regression task using the speechocean762 dataset and compared against duration-based models. Our results show that a model using the amplitude envelope's first derivative achieves the highest correlation with human-assigned scores on the Fluency and Prosody dimensions, producing significantly lower errors than one using segment durations among less fluent speakers. The findings support acoustic envelope features as robust, alignment-free alternatives for L2 rhythm assessment. Code is released publicly.

cs.SD↗

arXiv2026

User-Level Handover Decision Making Based on Machine Learning Approaches

This letter covers a broad comparison of methods for classification and regression applications for a user-level handover decision making in scenarios with adverse propagation conditions involving buildings, coverage holes, and shadowing effects. The simulation campaigns are based on network simulator ns-3. The comparison encompasses classical machine learning approaches, such as KNN, SVM, and neural networks, but also state-of-the-art fuzzy logic systems and latter boosting machines. The results indicate that SVM and MLP are the most suitable for the classification of the best handover target, although fuzzy system SOFL can perform similarly with lower processing time. Additionally, for the download time estimation, LightGBM provides the smallest error with short processing time, even in hard propagation scenarios.

cs.LG↗

arXiv2026

Large Language Model based air quality monitoring and localized alert generation

Poor indoor air quality can cause up to five times more direct health problems to occupants than outdoor air. In particular, it may cause headaches, fatigue, eye/throat irritation, and long-time exposure is linked to respiratory and heart as well as some forms of cancer. Despite the importance of indoor health and well-being, most current monitoring devices and systems (usually for offices and workspaces) are passive. The Environmental Quality Monitor (EnQyMo) platform is a generic Internet of Things (IoT) middleware designed to process several sensor data related to air quality in indoor spaces and correlate this data with health exposure risks of users/workplace employees. Using Bluetooth Low Energy (BLE) beacons and a mobile IoT middleware it is able to identify the (smartphone) users exposed to these polluted air or high CO2 (carbon dioxide) levels, and generate location-specific alarms only to the users at the places with the unhealthy air conditions. At the core of EnQyMo is an agency of Large Language Models (LLMs) capable of interpreting regulatory standards and scientific literature to automatically identify critical health exposure levels.

cs.DC↗

arXiv2025

Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech

Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks. Although promising results have been achieved, there is growing discussion regarding these models' generalization capabilities and the extent to which they truly integrate audio and text modalities in their internal representations. In this work, we evaluate four SLMs on the task of speech emotion recognition using a dataset of emotionally incongruent speech samples, a condition under which the semantic content of the spoken utterance conveys one emotion while speech expressiveness conveys another. Our results indicate that SLMs rely predominantly on textual semantics rather than speech emotion to perform the task, indicating that text-related representations largely dominate over acoustic representations. We release both the code and the Emotionally Incongruent Synthetic Speech dataset (EMIS) to the community.

cs.CL↗

arXiv2025

Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model

Emotion plays a fundamental role in human interaction, and therefore systems capable of identifying emotions in speech are crucial in the context of human-computer interaction. Speech emotion recognition (SER) is a challenging problem, particularly in natural speech and when the available data is imbalanced across emotions. This paper presents our proposed system in the context of the 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge. Our proposed architecture leverages cross-modality, utilizing cross-modal attention to fuse representations from different modalities. To address class imbalance, we employed two training designs: (i) weighted crossentropy loss (WCE); and (ii) WCE with an additional neutralexpressive soft margin loss and balancing. We trained a total of 12 multimodal models, which were ensembled using a balanced stacking model. Our proposed system achieves a MacroF1 score of 0.4094 and an accuracy of 0.4128 on 8-class speech emotion recognition.

eess.AS↗

arXiv2018

The long non-coding RNA HOTAIR is transcriptionally activated by HOXA9 and is an independent prognostic marker in patients with malignant glioma

The lncRNA HOTAIR has been implicated in several human cancers. Here, we evaluated the molecular alterations and upstream regulatory mechanisms of HOTAIR in glioma, the most common primary brain tumors, and its clinical relevance. HOTAIR gene expression, methylation, copy-number and prognostic value were investigated in human gliomas integrating data from online datasets and our cohorts. High levels of HOTAIR were associated with higher grades of glioma, particularly IDH wild-type cases. Mechanistically, HOTAIR was overexpressed in a gene dosage-independent manner, while DNA methylation levels of particular CpGs in HOTAIR locus were associated with HOTAIR expression levels in GBM clinical specimens and cell lines. Concordantly, the demethylating agent 5-Aza-2'-deoxycytidine affected HOTAIR transcriptional levels in a cell line-dependent manner. Importantly, HOTAIR was frequently co-expressed with HOXA9 in high-grade gliomas from TCGA, Oncomine, and our Portuguese and French datasets. Integrated in silico analyses, chromatin immunoprecipitation, and qPCR data showed that HOXA9 binds directly to the promoter of HOTAIR. Clinically, GBM patients with high HOTAIR expression had a significantly reduced overall survival, independently of other prognostic variables. In summary, this work reveals HOXA9 as a novel direct regulator of HOTAIR, and establishes HOTAIR as an independent prognostic marker, providing new therapeutic opportunities to treat this highly aggressive cancer.

q-bio.GN↗