arXiv AI
CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Scaling Audio Models Efficiently: Joint Optimization of Scale, Resolution, Adaptation, Precision, and Sparsity
The paper introduces a compression framework for the Whisper automatic speech recognition model that jointly optimizes six deployment dimensions—model size, temporal resolution, encoder token stride, low‑rank adaptation capacity, weight precision, and sparsity pattern—using NSGA‑III. The optimization targets three objectives: word error rate, inference FLOPs, and memory footprint. Evaluating 1,680 configurations, the study identifies compression combinations that outperform single‑axis scaling and notes that 1:4 structured sparsity cannot maintain acceptable accuracy within the tested budgets.
arXiv Computation and Language
2d ago
Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs
arXiv:2609.17981v1 Announce Type: cross Abstract: Speech Large Language Models (Speech-LLMs), typically built from a pre-trained speech encoder, a modality projector, and an LLM fine-tuned with Low-R...
arXiv AI
Jun 29
Measuring the Redundancy of Decoder Layers in SpeechLLMs
arXiv:2603. 05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters.
arXiv AI
Jun 11
Fast Speech Foundation Model Distillation Using Interleaved Stacking
arXiv:2606. 11766v1 Announce Type: cross Abstract: Distilling a large speech foundation model (SFM) into an efficient student model has been successfully applied to low-resource environments.
arXiv AI
Jun 3
Efficient ASR Training with Conversations that Never Happened
arXiv:2606. 03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data.
arXiv Computation and Language
4d ago
SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs
arXiv:2608.27783v3 Announce Type: replace-cross Abstract: Speech language models (speech LLMs) can generate plausible outputs from audio that contains no usable speech evidence. We study this failure...