paper-with-me

Papers

Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling

2020-01-25 · Hyun-Jin Park, Patrick Violette, Niranjan Subrahmanya

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.

📄 PDF Abstract BibTeX arXiv:2001.09246

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderKeyword Spottingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Adaptive Region Pooling for Object Detection

2015-06-01 · CVPR 2015 6 · Yi-Hsuan Tsai, Onur C. Hamsici, Ming-Hsuan Yang

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 Detection

Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting

2017-05-05 · Ming Sun, Anirudh Raju, George Tucker, Sankaran Panchapagesan 외

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 Spotting

Small-Footprint Open-Vocabulary Keyword Spotting with Quantized LSTM Networks

2020-02-25 · Théodore Bluche, Maël Primet, Thibault Gisselbrecht

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 Understanding

A Dynamic Reduction Network for Point Clouds

2020-03-18 · Lindsey Gray, Thomas Klijnsma, Shamik Ghosh

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+1

Feature Selective Networks for Object Detection

2017-11-24 · CVPR 2018 6 · Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li

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