#speech-llm

2 articles

01 ·Audio & Speech·★ MEMBER·PAPER·10 min read Paper Walkthrough: X-AuT — Pull Audio-Encoder Layers Out Two at a Time, Then Backfill from a Bigger Teacher Delete whole layers from a speech LLM's audio encoder and the decoder starts guessing 'end of sentence' too early, dropping characters. X-AuT picks which layers to remove with short trial runs, then backfills in three stages: distillation from a larger teacher, supervision on the student's own decoding context, and LoRA finetuning. Qwen3-ASR-0.6B goes from 18 to 16 layers with macro-average error falling 5.61% → 5.27%, and 14 layers land at 5.75% — single-run numbers, read here through the equations and the recipe. 02 ·Audio Codecs·★ MEMBER·PAPER·12 min read Neural Audio Codecs — EnCodec and the Foundation Under Speech LLMs MP3 and Opus were hand-designed around what the ear cannot hear. Neural audio codecs learn the coding itself and turn sound into a finite alphabet of integers. From vector quantization to residual VQ, EnCodec's bitrate arithmetic, and why VALL-E and AudioLM are built on top of it — starting from zero.