Despite rapid progress in the recent past, current speech recognition systems still require
labeled training data which limits this technology to a small fraction of the languages spoken …

Abstract Automatic Speech Recognition (ASR) systems can be trained to achieve
remarkable performance given large amounts of manually transcribed speech, but large …

Humans learn to speak before they can read or write, so why can't computers do the same?
In this paper, we present a deep neural network model capable of rudimentary spoken …

We present a novel approach to query-by-example keyword spotting (KWS) using a long
short-term memory (LSTM) recurrent neural network-based feature extractor. In our …

We investigate the problem of acoustic modeling in which prior language-specific
knowledge and transcribed data are unavailable. We present an unsupervised model that …

Recent studies have been revisiting whole words as the basic modelling unit in speech
recognition and query applications, instead of phonetic units. Such whole-word segmental …

Spoken term detection (STD) provides an efficient means for content based indexing of
speech. However, achieving high detection performance, faster speed, detecting ot-of …

In this paper, we design and develop RIO, a novel battery-free touch sensing user interface
(UI) primitive for future IoT and smart spaces. RIO enables UIs to be constructed using off-the …

In this paper, we present a method for learning discrete linguistic units by incorporating
vector quantization layers into neural models of visually grounded speech. We show that our …

This paper investigates the use of multidistribution deep neural networks (DNNs) for
mispronunciation detection and diagnosis (MDD), to circumvent the difficulties encountered …