Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The proposed new loss function allows training a model to detect parts and whole of a keyword, without strictly depending on frame-level labeling from LVCSR (Large vocabulary continuous speech recognition), making further optimization possible. The proposed system outperforms the baseline keyword spotting model in [1] due to increased optimizability. Further, it can be more easily adapted for on-device learning applications due to reduced dependency on LVCSR.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderKeyword Spottingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adaptive Region Pooling for Object Detection
Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method tha…
Objectobject-detectionObject DetectionMax-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training c…
CPUKeyword SpottingSmall-Footprint Keyword SpottingSmall-Footprint Open-Vocabulary Keyword Spotting with Quantized LSTM Networks
We explore a keyword-based spoken language understanding system, in which the intent of the user can directly be derived from the detection of a sequence of keywords in the query. In this paper, we focus on an open-vocab…
Keyword SpottingSpoken Language UnderstandingA Dynamic Reduction Network for Point Clouds
Classifying whole images is a classic problem in machine learning, and graph neural networks are a powerful methodology to learn highly irregular geometries. It is often the case that certain parts of a point cloud are m…
ClusteringGeneral Classificationimage-classificationImage Classification+1Feature Selective Networks for Object Detection
Objects for detection usually have distinct characteristics in different sub-regions and different aspect ratios. However, in prevalent two-stage object detection methods, Region-of-Interest (RoI) features are extracted …
Objectobject-detectionObject DetectionTranslation