arXiv:2503. 00340v2 Announce Type: cross Abstract: Lightweight models are essential for real-time speech enhancement applications.
arXiv:2606. 12662v1 Announce Type: cross Abstract: Speech enhancement models typically apply uniform capacity across all frequencies, disregarding the non-uniform spectral resolution of human hearing.
arXiv:2601. 06199v3 Announce Type: replace-cross Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form speech is bottlenecked by the explosive growth of input tokens.
arXiv:2604. 01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge.
arXiv:2510. 20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications.
arXiv:2606. 10046v1 Announce Type: cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque.
arXiv:2607. 10191v1 Announce Type: cross Abstract: Generative streaming models for Target Speaker Extraction (TSE) commonly exhibit a quality--intelligibility trade-off, wherein naive optimization for perceptual audio quality tends to degrade speech intelligibility, and conversely.
arXiv:2606. 03359v1 Announce Type: cross Abstract: Speech emotion recognition is an important component of modern human-computer interaction systems.
arXiv:2608. 08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks.
arXiv:2510. 12947v3 Announce Type: replace-cross Abstract: Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices.
arXiv:2606. 14647v1 Announce Type: cross Abstract: Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret.
Speech emotion recognition is an important component of modern human-computer interaction systems. However, many state-of-the-art approaches rely on large pretrained models with high computational and memory requirements, limiting their applicability.
arXiv:2509. 00078v2 Announce Type: replace-cross Abstract: The emergence of large language models (LLMs) has transformed spoken dialog systems, yet the optimal architecture for real-time on-device voice agents remains an open question.