Text-aware Speech Separation for Multi-talker Keyword Spotting
For noisy environments, ensuring the robustness of keyword spotting (KWS) systems is
essential. While much research has focused on noisy KWS, less attention has been paid to …
essential. While much research has focused on noisy KWS, less attention has been paid to …
Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection
M Ryu, JW Kim, M Oh, S Lee, H Park - arXiv preprint arXiv:2501.11631, 2025 - arxiv.org
Keyword spotting is often implemented by keyword classifier to the encoder in acoustic
models, enabling the classification of predefined or open vocabulary keywords. Although …
models, enabling the classification of predefined or open vocabulary keywords. Although …
Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency
Connectionist Temporal Classification (CTC), a non-autoregressive training criterion, is
widely used in online keyword spotting (KWS). However, existing CTC-based KWS …
widely used in online keyword spotting (KWS). However, existing CTC-based KWS …
OPC-KWS: Optimizing Keyword Spotting with Path Retrieval Decoding and Contrastive Learning
J Li, X Liu, X Zhang - 2024 IEEE 14th International Symposium …, 2024 - ieeexplore.ieee.org
As voice interaction capabilities with smart devices advance and the demand for
personalized wake words increases, customized keyword spotting (KWS) has become …
personalized wake words increases, customized keyword spotting (KWS) has become …