Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics.
arXiv:2606. 22790v2 Announce Type: replace-cross Abstract: In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER).
By Vyom Agarwal, Mokshda Gangrade, Siddharth Pal, Jerry Wu
arXiv:2609.39453v1 Announce Type: cross
Abstract: Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent app...
By Hezhao Zhang, Thomas Hain
arXiv:2608. 05165v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data.
By Ali Shendabadi, Parnia Izadirad, Mostafa Salehi
arXiv:2606. 10278v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) aims to identify a speaker's emotional state from audio signals.
By Youcef Soufiane Gheffari, Samiya Silarbi
The paper introduces RAFM-SER++, a lightweight multimodal speech emotion recognition framework designed for real‑time surveillance systems. It replaces heavy bidirectional cross‑modal transformers with an asymmetric Residual Attention Fusion Mechanism that injects affective speech cues into text representations via a one‑directional residual attention pathway. Experiments on IEMOCAP and ESD show RAFM‑SER++ outperforms the HuBERT‑Base baseline and MemoCMT, reducing trainable parameters by over 60%, achieving 79.60 it/s inference speed, and reaching BACC scores of 81.10% on IEMOCAP and 95.39% on ESD.
By Ngo Truong Dinh, Tung-Lam Bui, Chi-Trung Duong, Vien Nguyen Thi, Viet-Anh Nguyen, Phuc-Lu Le
arXiv:2512.07571v3 Announce Type: replace
Abstract: This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tune...
By Nicolas Calbucura, Jose Guillen, Valentin Barriere
arXiv:2606. 07309v1 Announce Type: cross Abstract: Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available.
By Iosif Tsangko, Andreas Triantafyllopoulos, Bj\"orn W. Schuller
arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.
By Maris Basha, Anja Zai, Sabine Stoll, Richard Hahnloser
arXiv:2607. 16803v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) is an important component in a wide range of human-centered applications, including healthcare, customer service, and human-omputer interaction.
By Nelly Elsayed
EMODY Flow is a lightweight flow‑matching framework that generates synchronized full‑body motion and facial expressions conditioned on speech and emotion. It attaches to a frozen Qwen‑3 Omni model, reusing its audio codecs to drive two parallel DiT generators for SMPL‑X body pose and FLAME facial expressions. An auxiliary emotion classifier at training time restores emotion sensitivity, enabling EMODY Flow to achieve state‑of‑the‑art gesture quality on BEAT2 and zero‑shot facial animation on TFHP, with significant improvements in FGD, Beat Correlation, and Diversity metrics.
By Harsh Kumar Agarwal, Xavier Alameda-Pineda, Olivier Perrotin
The paper introduces a geometry-aware hyperbolic residual quantization method for variational autoencoders, addressing inconsistencies that arise when extending residual vector quantization to hyperbolic space. It restores telescoping behavior in the forward pass via Hyperbolic Residual Aggregation and improves gradient flow in the backward pass with a discounted Hyperbolic Straight-Through Estimator. Experiments on hierarchical prediction, recommendation, image tokenization, and neural audio coding demonstrate enhanced stability and structural organization of hyperbolic residual codes, while highlighting a trade‑off between compression efficiency and hierarchical organization.
By Alessio Colombo, Melika Ayoughi