paper-with-me

홈 › Papers

AdaKWS: Towards Robust Keyword Spotting with Test-Time Adaptation

2025-05-20 · Yang Xiao, Tianyi Peng, Yanghao Zhou, Rohan Kumar Das

Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in unseen environments or noisy backgrounds. Test-time adaptation (TTA) helps models adapt to test samples without needing the original training data. In this study, we present AdaKWS, the first TTA method for robust KWS to the best of our knowledge. Specifically, 1) We initially optimize the model's confidence by selecting reliable samples based on prediction entropy minimization and adjusting the normalization statistics in each batch. 2) We introduce pseudo-keyword consistency (PKC) to identify critical, reliable features without overfitting to noise. Our experiments show that AdaKWS outperforms other methods across various conditions, including Gaussian noise and real-scenario noises. The code will be released in due course.

📄 PDF Abstract BibTeX arXiv:2505.14600

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword SpottingTest-time Adaptation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Open-vocabulary Keyword-spotting with Adaptive Instance Normalization

2023-09-13 · Aviv Navon, Aviv Shamsian, Neta Glazer, Gill Hetz 외

Open vocabulary keyword spotting is a crucial and challenging task in automatic speech recognition (ASR) that focuses on detecting user-defined keywords within a spoken utterance. Keyword spotting methods commonly map th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Keyword Spottingspeech-recognition+1

On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems

2024-03-12 · Cristian Cioflan, Lukas Cavigelli, Manuele Rusci, Miguel de Prado 외

Keyword spotting accuracy degrades when neural networks are exposed to noisy environments. On-site adaptation to previously unseen noise is crucial to recovering accuracy loss, and on-device learning is required to ensur…

Domain AdaptationKeyword Spotting

Personalized Keyword Spotting through Multi-task Learning

2022-06-28 · Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang

Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. Howeve…

Keyword SpottingMulti-Task LearningSpeaker Verification

Towards On-device Domain Adaptation for Noise-Robust Keyword Spotting

2022-06-13 · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) 2022 6 · Cristian Cioflan, Lukas Cavigelli, Manuele Rusci, Miguel de Prado 외

The accuracy of a keyword spotting model deployed on embedded devices often degrades when the system is exposed to real environments with significant noise. In this paper, we explore a methodology for tailoring a model t…

Edge-computingKeyword Spotting

DONUT: CTC-based Query-by-Example Keyword Spotting

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

Keyword spotting—or wakeword detection—is an essential feature for hands-free operation of modern voice-controlled devices. With such devices becoming ubiquitous, users might want to choose a personalized custom wakeword…

Keyword Spotting