Takumi Kurokawa

Robust Query-by-example Spoken Term Detection for Unknown Words Using Speech Retrieval-oriented E2E ASR Modeling

2021 · 2021 IEEE 10th Global Conference on Consumer Electronics (GCCE)

Query-by-example spoken term detection (STD) systems can make good use of automatic speech recognition (ASR), especially when the error rate is low. However, ASR suffers from the out-of-vocabulary (OOV) problem. The OOV problem in the …