Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2501.12682

EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model

Rashedul Hasan·Meher Nigar·Nursadul Mamun·Sayan Paul
View original source ↗Read source document ↗Export metadata ↓

Abstract

Speech Emotion Recognition is a crucial area of research in human-computer interaction. While significant work has been done in this field, many state-of-the-art networks struggle to accurately recognize emotions in speech when the data is both speech and speaker-independent. To address this limitation, this study proposes, EmoFormer, a hybrid model combining CNNs (CNNs) with Transformer encoders to capture emotion patterns in speech data for such independent datasets. The EmoFormer network was trained and tested using the Expressive Anechoic Recordings of Speech (EARS) dataset, recently released by META. We experimented with two feature extraction techniques: MFCCs and x-vectors. The model was evaluated on different emotion sets comprising 5, 7, 10, and 23 distinct categories. The results demonstrate that the model achieved its best performance with five emotions, attaining an accuracy of 90%, a precision of 0.92, a recall, and an F1-score of 0.91. However, performance decreased as the number of emotions increased, with an accuracy of 83% for seven emotions compared to 70% for the baseline network. This study highlights the effectiveness of combining CNNs and Transformer-based architectures for emotion recognition from speech, particularly when using MFCC features.

Explore related subjects

eess.AScs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Rashedul Hasan, Meher Nigar, Nursadul Mamun, Sayan Paul. 2025-01-22. EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model. https://arxiv.org/abs/2501.12682

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Revisiting Lexicon Evaluation in Unsupervised Word Discovery

Building a lexicon from discovered word-like units is a central goal in zero-resource speech processing. But do our evaluations provide a trustworthy indication of lexicon quality? A common metric, normalized edit distance, averages the phoneme edit distances between discovered units in each cluster. We show that this metric has an inherent bias toward the quality of large clusters, inhibiting fair evaluation. Moreover, it ignores how well true classes are distributed across clusters. Based on established theory in clustering literature, we propose two metrics that address these shortcomings: a modified metric that weighs cluster size when assessing within-cluster consistency, and an inverse metric that assesses how true words are spread across clusters. Through experiments on synthetic and real-world lexicons, we demonstrate that combined, these metrics are: (1) more closely correlated with how similar a lexicon is to the ground-truth distribution, and (2) more robust to biases that skew lexicon evaluations.

eess.AS↗
arXiv2026

AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models

Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs contain no speech, weak acoustic evidence, or unreliable transcription. We propose AURA: Activation-editing with Uncertainty-Routed Adaptation, an ultra-efficient representation-editing method that freezes the pretrained model and applies sparse scale-and-shift edits to decoder cross-attention heads. AURA dynamically routes edits using cross-attention uncertainty features that capture over-concentration, diffuse attention, and abrupt frame shifts. We evaluate AURA on four datasets spanning non-speech hallucination and speech grounding stressors, including imperfect-label child speech, imperfect-label adult speech, and disfluent speech. On non-speech audio, AURA reduces hallucination rate from 89.18% to 1.94% without prior hallucination-head identification. On imperfect-label corpora, AURA approaches LoRA WER while using roughly 500x fewer trainable parameters. Sensitivity analysis and qualitative cross-attention examples are consistent with AURA's uncertainty-routed editing behavior, supporting dynamic activation editing as a practical path for grounding AED speech models.

eess.AS↗
arXiv2026

The design of an optomechanical microphone using a photonic waveguide interferometer

We present an optomechanical microphone based on a diaphragm-integrated photonic waveguide Mach-Zehnder interferometer. Acoustic pressure deforms the MEMS diaphragm, inducing strain in the sensing waveguide and changing its optical path length. We analytically evaluate the optical and mechanical transduction mechanisms and key figures of merit, including signal-to-noise ratio, dynamic range, acoustic overload pressure, and minimum detectable pressure. Two design cases are considered: a MEMS microphone and a measurement microphone. The results indicate competitive performance but no substantial overall advantage over state-of-the-art microphones in conventional applications. The architecture may nevertheless offer advantages for high-temperature and other harsh-environment sensing applications.

eess.AS↗