A comprehensive survey and analysis of generative models in machine learning
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 …
learning, we come across many scenarios when directly learning a target is intractable …
An overview of noise-robust automatic speech recognition
New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …
with mobile devices and home entertainment systems, increasingly require automatic …
Deepear: robust smartphone audio sensing in unconstrained acoustic environments using deep learning
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 …
audio sensing is highly susceptible to wild fluctuations in accuracy when used in diverse …
The subspace Gaussian mixture model—A structured model for speech recognition
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 …
(HMM) states share the same Gaussian Mixture Model (GMM) structure with the same …
Machine learning in automatic speech recognition: A survey
J Padmanabhan… - IETE Technical Review, 2015 - Taylor & Francis
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 …
paradigms used in automatic speech recognition (ASR) for home automation to space …
Minimum bayes risk decoding and system combination based on a recursion for edit distance
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 …
decoding for speech recognition. Our algorithm can take as input either a single lattice, or …
Revisiting hidden Markov models for speech emotion recognition
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 …
due to their capability of capturing temporal dynamic characteristics of speech. For emotion …
Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models
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 …
found to be very difficult to improve over separately trained systems. The usual approach …
Multitask learning of deep neural networks for low-resource speech recognition
D Chen, BKW Mak - IEEE/ACM Transactions on Audio, Speech …, 2015 - ieeexplore.ieee.org
We propose a multitask learning (MTL) approach to improve low-resource automatic speech
recognition using deep neural networks (DNNs) without requiring additional language …
recognition using deep neural networks (DNNs) without requiring additional language …
Spoken content retrieval—beyond cascading speech recognition with text retrieval
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 …
the audio rather than text descriptions. This potentially eliminates the requirement of …