Deep learning for environmentally robust speech recognition: An overview of recent developments

Z Zhang, J Geiger, J Pohjalainen, AED Mousa… - ACM Transactions on …, 2018‏ - dl.acm.org
Eliminating the negative effect of non-stationary environmental noise is a long-standing
research topic for automatic speech recognition but still remains an important challenge …

A Survey on Machine Learning‐Based Mobile Big Data Analysis: Challenges and Applications

J **e, Z Song, Y Li, Y Zhang, H Yu… - Wireless …, 2018‏ - Wiley Online Library
This paper attempts to identify the requirement and the development of machine learning‐
based mobile big data (MBD) analysis through discussing the insights of challenges in the …

Text-independent speaker verification based on triplet convolutional neural network embeddings

C Zhang, K Koishida… - IEEE/ACM Transactions on …, 2018‏ - ieeexplore.ieee.org
The effectiveness of introducing deep neural networks into conventional speaker recognition
pipelines has been broadly shown to benefit system performance. A novel text-independent …

Sequence summarizing neural network for speaker adaptation

K Veselý, S Watanabe, K Žmolíková… - … on acoustics, speech …, 2016‏ - ieeexplore.ieee.org
In this paper, we propose a DNN adaptation technique, where the i-vector extractor is
replaced by a Sequence Summarizing Neural Network (SSNN). Similarly to i-vector …

Factorized hidden layer adaptation for deep neural network based acoustic modeling

L Samarakoon, KC Sim - IEEE/ACM Transactions on Audio …, 2016‏ - ieeexplore.ieee.org
In this paper, we propose the factorized hidden layer (FHL) approach to adapt the deep
neural network (DNN) acoustic models for automatic speech recognition (ASR). FHL aims at …

Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions

M Delcroix, K Kinoshita, C Yu, A Ogawa… - … , Speech and Signal …, 2016‏ - ieeexplore.ieee.org
Deep neural network (DNN) based acoustic models have greatly improved the performance
of automatic speech recognition (ASR) for various tasks. Further performance improvements …

A study of speaker verification performance with expressive speech

S Parthasarathy, C Zhang… - … on Acoustics, Speech …, 2017‏ - ieeexplore.ieee.org
Expressive speech introduces variations in the acoustic features affecting the performance
of speech technology such as speaker verification systems. It is important to identify the …

Predicting speaker recognition reliability by considering emotional content

S Parthasarathy, C Busso - 2017 seventh international …, 2017‏ - ieeexplore.ieee.org
Studies have shown that emotional variability in speech degrades the performance of
speaker recognition tasks. Of particular interest is the error produced due to mismatch …

[PDF][PDF] 2016 BUT Babel System: Multilingual BLSTM Acoustic Model with i-Vector Based Adaptation.

M Karafiát, MK Baskar, P Matejka, K Veselý… - …, 2017‏ - researchgate.net
The paper provides an analysis of BUT automatic speech recognition systems (ASR) built for
the 2016 IARPA Babel evaluation. The IARPA Babel program concentrates on building ASR …

Robust feature extraction and uncertainty estimation based on attractor dynamics in cyclic deep denoising autoencoders

AH Hadjahmadi, MM Homayounpour - Neural Computing and Applications, 2019‏ - Springer
Because the input and the output values of the deep denoising autoencoders (DDAs) have
the same representation space, the output values of a DDA can be used as its input values …