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: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
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