paper-with-me

홈 › Papers

GraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples

2025-05-20 · Harry Zhang, Kurt Partridge, Pai Zhu, Neng Chen, Hyun Jin Park, Dhruuv Agarwal, Quan Wang

Spoken Keyword Spotting (KWS) is the task of distinguishing between the presence and absence of a keyword in audio. The accuracy of a KWS model hinges on its ability to correctly classify examples close to the keyword and non-keyword boundary. These boundary examples are often scarce in training data, limiting model performance. In this paper, we propose a method to systematically generate adversarial examples close to the decision boundary by making insertion/deletion/substitution edits on the keyword's graphemes. We evaluate this technique on held-out data for a popular keyword and show that the technique improves AUC on a dataset of synthetic hard negatives by 61% while maintaining quality on positives and ambient negative audio data.

📄 PDF Abstract BibTeX arXiv:2505.14814

Code (0)

등록된 구현이 없습니다.

Tasks

Keyword Spotting

Similar Papers 제목 키워드 기반

Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval

2026-04-20 · HaeJun Yoo, Yongseop Shin, Insung Lee, Myoung-Wan Koo 외 arxiv

Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially …

Text Retrieval

When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance

2026-06-24 · Bo Chen arxiv

Can a statistically significant, large-effect-size finding in computational social science be entirely an artifact of the measurement instrument? We present a case where the answer appears to be yes. Analyzing 85 intervi…

Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting

2024-08-20 · Hyun Jin Park, Dhruuv Agarwal, Neng Chen, Rentao Sun 외

The keyword spotting (KWS) problem requires large amounts of real speech training data to achieve high accuracy across diverse populations. Utilizing large amounts of text-to-speech (TTS) synthesized data can reduce the …

Keyword Spottingtext-to-speechText to Speech

FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction

2026-06-02 · Chang Kong, Yuebing Li, Peng Mo, Haigang Zhang 외 arxiv

The scarcity of hard negative samples in current vision-language datasets significantly hinders fine-grained perception. To address this, we propose FineGen, a VLM-based Multi-Agent framework for automated dataset constr…

Training Keyword Spotters with Limited and Synthesized Speech Data

2020-01-31 · James Lin, Kevin Kilgour, Dominik Roblek, Matthew Sharifi

With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in…

Keyword Spotting