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:2609.14956v1 Announce Type: cross Abstract: Speech Quality Assessment (SQA) is essential for modern speech technologies, and recent non-intrusive SQA predictors increasingly rely on Speech Foun...
arXiv:2604. 08558v2 Announce Type: replace-cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention.
arXiv:2601. 19919v2 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is one of the most effective paradigms for compressing large-scale foundation models into deployable architectures.
RT-SEMamba is a fully causal speech enhancement model that uses causal time‑frequency Mamba blocks instead of Transformer‑based architectures, allowing efficient long‑form inference with a fixed‑size recurrent state. The authors introduce a progressive knowledge distillation strategy that compresses an 8‑layer teacher into a single‑layer student by jointly distilling spectral outputs and intermediate representations. On the Voicebank‑DEMAND benchmark, the 8‑layer model achieves 3.32 PESQ under a 25 ms latency constraint, while the distilled 1‑layer student improves from 3.06 to 3.18 PESQ, maintains the same steady‑state real‑time factor, and runs 2.64× faster than the teacher.
arXiv:2603. 01875v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones.
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:2609.36324v1 Announce Type: cross Abstract: Flow-matching text-to-speech (TTS) models achieve high synthesis quality but require many neural function evaluations (NFEs) to integrate their gener...
X-AuT is a progressive framework for compressing the audio encoder of speech large language models. It selects layer combinations via short behavioral probes and restores performance through representation alignment, cross‑scale distillation, scheduled student‑policy supervision, and LoRA finetuning, while keeping the language‑model backbone frozen. On ten Chinese–English benchmarks, reducing Qwen3‑ASR‑0.6B’s encoder from 18 to 16 layers lowers macro‑average error from 5.61% to 5.27%, and a 14‑layer model achieves 5.75% error with 20.7% fewer parameters.
arXiv:2603. 15590v2 Announce Type: replace Abstract: There have been numerous attempts to distill quadratic attention-based large language models (LLMs) into sub-quadratic linearized architectures.
arXiv:2609.21672v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeab...
arXiv:2506. 01503v2 Announce Type: replace Abstract: With the rise of large pre-trained foundation models for automatic speech recognition new challenges appear.
arXiv:2603. 24596v3 Announce Type: replace-cross Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts.