Papers with DTW
Corpus Generation for Voice Command in Smart Home and the Effect of Speech Synthesis on End-to-End SLU (2020.lrec-1)
Copied to clipboard
| Challenge: | Massive amounts of annotated data are often unavailable for novel tasks performed in real-world environments such as smart homes. |
| Approach: | They propose to use a synthetic semantically-annotated corpus of French commands for smart-home to train pipeline and end-to-end (E2E) SLU models. |
| Outcome: | The proposed model trains pipeline and end-to-end (E2E) SLU models on voice commands acquired in a real smart home. |
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs (2026.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) is a useful tool for accelerating large language models . but its utility is limited by a fundamental constraint: draft and target models must share the same vocabulary . |
| Approach: | They propose an algorithm that uses a draft token sequence to get a new target token sequence and then uses DTW to build a mapping to transfer probability distributions. |
| Outcome: | The proposed method shows 1.57x speedup on various tasks. |