Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application...

We propose a method for finding keywords in an audio database using a spoken query. Our method is based on performing a joint alignment between a phone lattice generated from a spoken utterance query and a second phone lattice representing a long utterance needing to be searched. We implement this joint alignment procedure in a graphical models framework. We evaluate our system on TIMIT as well...

In this paper, an auto-attendant system using finite state grammar (FSG) based on a continuous speech recognition (CSR) model is introduced. However, by using two virtual garbage models, one is to match the leading extraneous speech before the key name and the other to match the tailing extraneous speech following the key name, we managed to reach a more flexible and robust auto-attendant syste...

Multimedia databases contain an increasing amount of videos that are hardly semantically accessed. Among the useful indices that can be extracted from the sound track, the presence of a keyword at some place plays a prominent role. This paper deals with the specificities of such a keyword spotter and the enhancement brought to our previous technique, [1] based on frame labeling. To be useful, s...

In this paper, we propose a novel Low-Power Feature-Attention Chinese Keyword Spotting Framework based on depthwise separable convolution neural network (DSCNN) with distillation learning to recognize speech signals of wake-up words. The framework consists low-power feature-attention acoustic model and its methods. Different from the existing model, proposed connectionist temporal classificatio...

Multimedia databases contain an increasing amount of videos that are hardly semantically accessed. Among the useful indices that can be extracted from the sound track, the presence of a keyword at some place plays a prominent role. This paper deals with the specificities of such a keyword spotter and the enhancement brought to our previous technique, [1] based on frame labeling. To be useful, s...

Keyword spotting (KWS) aims to detect predefined keywords in continuous speech. Recently, direct deep learning approaches have been used for KWS and achieved great success. However, these approaches mostly assume fixed keyword vocabulary and require significant retraining efforts if new keywords are to be detected. For unrestricted vocabulary, HMM based keywordfiller framework is still the main...

Our goal is to design an accurate keyword spotter that can deal with any size of keyword set, since the size actually required in a wide range of applications is large (number of airports, number of names in a directory, etc.). This justi es the choice of an architecture based on a large-vocabulary continuous-speech recognizer. In a previous paper [1] we introduced the use of strictly-lexical s...