# Streamalign-SLM (R16)

StreamAlign speech language model (Llama-3.2-1B backbone, R16 hier
durfirst-durreg, text-KL recipe). Scores speech via the paired R16 RVQ
teacher `Streamalign-R16`.

- Speech tokenizer / teacher: `Streamalign-R16`
- Reported metrics: SALMon 69.1 (4-task, no pitch), StoryCloze 72.1 (sSC 59.0 / tSC 85.1)

## Citation

Accepted to **Findings of EMNLP 2026**.

```bibtex
@inproceedings{kim2026streamalign,
  title     = {{StreamAlign: Streaming Text-Aligned Speech Tokenization}},
  author    = {Kim, Kang-wook and Park, Jinyoung and Kim, Jinsoo and
               Lee, Sehun and Woo, Tony and Kim, Gunhee},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year      = {2026}
}
```