# Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up

arXiv: https://arxiv.org/abs/2609.12469 · HTML: https://mlsanity.com/paper/2609.12469/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 14 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems](https://mlsanity.com/paper/1605.07669/) (2016)
- [Personalized Speech recognition on mobile devices](https://mlsanity.com/paper/1603.03185/) (2016)
- [Device-directed Utterance Detection](https://mlsanity.com/paper/1808.02504/) (2018)
- [Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers](https://mlsanity.com/paper/2008.00508/) (2020)
- [Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation](https://mlsanity.com/paper/2008.08113/) (2020)
- [FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistants](https://mlsanity.com/paper/2109.09958/) (2021)

## Abstract (arXiv)

False wake-up activations remain a persistent challenge in conversational AI. Speech phonetically similar to a device's wake word can produce a syntactically valid and semantically coherent ASR transcript that the assistant incorrectly executes. Most existing systems make a single intent decision in isolation, without a mechanism to learn from recurring errors over time or adapt to individual users through personalized learning. We introduce the Feedback-Driven Adaptive Self-Correcting Inference Layer (ASCIL), a complementary post-ASR correction framework that re-evaluates wake-up intent before response generation by fusing acoustic embeddings, linguistic cues, device context, and patterns from past misclassifications. ASCIL interprets implicit signals, including hesitation, disengagement, and silence, and explicit signals, including cancellation and repetition, as automatically inferred, noisy behavioral indicators of potential misclassification. These signals drive online pattern updates without manual annotation, whereas the intentional/unintentional reference labels used for offline evaluation are human-annotated. It generalizes from prior errors, applies corrective adjustments at inference time, and continuously updates in parallel with natural-language execution. Evaluated on a proprietary dataset of 3,667 interactions with human-annotated intentional/unintentional reference labels spanning 14 acoustic and contextual conditions, ASCIL achieves 54.27% relative error reduction on a session-disjoint subset constructed from baseline failures, and up to 24.39% relative error reduction at threshold 0.90 on the issue-tagged evaluation slice. These gains are achieved while improving intentional acceptance rates, with a median added latency below 60 ms in the reported benchmark.