Several consumer speech devices feature voice interfaces that perform on-device keyword spotting to initiate user interactions. Accurate on-device keyword spotting within a tight CPU budget is crucial for such devices. Motivated by this, we investigated two ways to improve deep neural network (DNN) acoustic models for keyword spotting without increasing CPU usage. First, we used low-rank weight...

Keyword spotting (KWS) is becoming a ubiquitous need with the advancement in artificial intelligence and smart devices. Recent work this field have focused on several different architectures to achieve good results datasets low moderate noise. However, performance of these models deteriorates under high noise conditions as shown by our experiments. In paper, we present an extensive comparison b...

HarkMan keyword-spotter was designed so that it can be used in a real-world environment to automatically spot the given words of a vocabulary-independent (VIND) task in unconstrained Chinese telephone speech. In this spotter, the speaking manner and the number of keywords are not limited. This paper focuses on a novel technique that addresses acoustic modeling, keyword-spotting network, search ...

For many practical applications of keyword spotting, input signal is a spontaneous conversation while the acoustic model was trained with read speech because of data availability. Generally speaking, keyword spotting system will degrade significantly because of mismatch between acoustic model and spontaneous speech. To solve this problem, this paper presents a two-pass keyword spotting strategy...

The recent development of embedded platforms along with spectacular growth in communication networking technologies is driving the Internet of things to thrive. More complex tasks are now possible to operate in small devices such as speech recognition and keyword spotting which are in great demand. Traditional voice recognition approaches are already being used in several embedded applications,...

In this paper, a new hybrid approach is presented for keyword spotting. The proposed Method is based on Hidden Markov Mode (HMM) and is performed in two stages. In the first stage by using phoneme models, a series of candidate keyword(s) is recognized. In the second stage, word models are used to decide on acceptance or rejection of each candidate keyword. Two different methods are presented in...

In telephone speech recognition, the acoustic mismatch between the training and the test environment often causes severe degradation due to the channel distortion and ambient noise. In this paper, a two-level codebook-based stochastic matching (CBSM) is proposed to deal with the acoustic mismatch. For multi-keyword detection, we define a keyword relation table and a weighting function for reaso...

We are developing a spoken dialogue system that accepts speaker-independent continuous utterances and responds to them. Two approaches are adopted and compared. Syntax-driven approach first applies syntactic analysis to constrain the input and passes syntactically accepted sentence candidates to semantic analysis. Keyword-driven approach performs keyword spotting and generates a lattice of keyw...