Generative models have been in existence for many decades. In the field of machine
learning, we come across many scenarios when directly learning a target is intractable …

New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …

Microphones are remarkably powerful sensors of human behavior and context. However,
audio sensing is highly susceptible to wild fluctuations in accuracy when used in diverse …

We describe a new approach to speech recognition, in which all Hidden Markov Model
(HMM) states share the same Gaussian Mixture Model (GMM) structure with the same …

Over the past few decades, there has been tremendous development in machine learning
paradigms used in automatic speech recognition (ASR) for home automation to space …

In this paper we describe a method that can be used for Minimum Bayes Risk (MBR)
decoding for speech recognition. Our algorithm can take as input either a single lattice, or …

Hidden Markov models (HMMs) have a long tradition in automatic speech recognition (ASR)
due to their capability of capturing temporal dynamic characteristics of speech. For emotion …

Although research has previously been done on multilingual speech recognition, it has been
found to be very difficult to improve over separately trained systems. The usual approach …

We propose a multitask learning (MTL) approach to improve low-resource automatic speech
recognition using deep neural networks (DNNs) without requiring additional language …

Spoken content retrieval refers to directly indexing and retrieving spoken content based on
the audio rather than text descriptions. This potentially eliminates the requirement of …