Keyword spotting (KWS) utilities have become increasingly popular on a wide range of mobile and home devices, representing prolific application field for Convolutional Neural Networks (CNNs), which are commonly exploited to perform keyword classification. Addressing the challenges targeting such resource-constrained platforms, requires careful definition CNN architecture overall system implemen...

This paper investigates the usage of prosody for the improvement of keyword spotting, focusing on the highly agglutinating Hungarian language, where keyword spotting cannot be effectively performed using LVCSR, as such systems are either unavailable or hard to operate due to high OOV rates and poor Ngram language modelling capabilities. Therefore, the applied keyword spotting system is based on...

This paper describes topic identi cation for Japanese TV news speech based on the keyword spotting technique. Three thousands of nouns are selected as keywords which contribute to topic identi cation, based on criterion of mutual information and a length of the word. This set of the keywords identi ed the correct topic for 76.3% of articles from newspaper text data. Further, we performed keywor...

We present a cascade architecture for keyword spotting with speaker verification on mobile devices. By pairing a small computational footprint with specialized digital signal processing (DSP) chips, we are able to achieve low power consumption while continuously listening for a keyword.

Many students use videos to supplement learning outside the classroom. This is particularly important for students with challenged visual capacities, for whom seeing the board during lecture is di cult. For these students, we believe that recording the lectures they attend and providing e↵ective video indexing and search tools will make it easier for them to learn course subject matter at their...

A ternary-weight neural network (TWN) inspired keyword spotting (KWS) processor is proposed to support complicated and variable application scenarios. To achieve high-precision recognition of 10 keywords under 5dB Clean wide range background noises, a convolution consists 4 layers fully connected layers, with modified sparsity-controllable Truncated Gaussian Approximation based training used. E...