A survey on machine learning in Internet of Things: Algorithms, strategies, and applications
In the IoT and WSN era, large number of connected objects and sensing devices are
dedicated to collect, transfer, and generate a huge amount of data for a wide variety of fields …
dedicated to collect, transfer, and generate a huge amount of data for a wide variety of fields …
Multilingual sentiment analysis: from formal to informal and scarce resource languages
The ability to analyse online user-generated content related to sentiments (eg, thoughts and
opinions) on products or policies has become a de-facto skillset for many companies and …
opinions) on products or policies has become a de-facto skillset for many companies and …
Context dependent recurrent neural network language model
Recurrent neural network language models (RNNLMs) have recently demonstrated state-of-
the-art performance across a variety of tasks. In this paper, we improve their performance by …
the-art performance across a variety of tasks. In this paper, we improve their performance by …
Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition
X Li, X Wu - 2015 ieee international conference on acoustics …, 2015 - ieeexplore.ieee.org
Long short-term memory (LSTM) based acoustic modeling methods have recently been
shown to give state-of-the-art performance on some speech recognition tasks. To achieve a …
shown to give state-of-the-art performance on some speech recognition tasks. To achieve a …
A pitch extraction algorithm tuned for automatic speech recognition
In this paper we present an algorithm that produces pitch and probability-of-voicing
estimates for use as features in automatic speech recognition systems. These features give …
estimates for use as features in automatic speech recognition systems. These features give …
Improving deep neural network acoustic models using generalized maxout networks
Recently, maxout networks have brought significant improvements to various speech
recognition and computer vision tasks. In this paper we introduce two new types of …
recognition and computer vision tasks. In this paper we introduce two new types of …
Multilingual training of deep neural networks
We investigate multilingual modeling in the context of a deep neural network (DNN)-hidden
Markov model (HMM) hybrid, where the DNN outputs are used as the HMM state likelihoods …
Markov model (HMM) hybrid, where the DNN outputs are used as the HMM state likelihoods …
Silent speech recognition as an alternative communication device for persons with laryngectomy
Each year thousands of individuals require surgical removal of the larynx (voice box) due to
trauma or disease, and thereby require an alternative voice source or assistive device to …
trauma or disease, and thereby require an alternative voice source or assistive device to …
Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification
In this paper, we describe recent progress in i-vector based speaker verification. The use of
universal background models (UBM) with full-covariance matrices is suggested and …
universal background models (UBM) with full-covariance matrices is suggested and …
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 …