Results 271 to 280 of about 16,736,389 (319)

The effect of orthokeratology lens optical zone size on myopia control in adolescents. [PDF]

Front Med (Lausanne)
Lai L, Long W, Zheng B, Liang Z, He Z, Chen L, Cui D.   +6 more
europepmc   +1 more source

Direct all-electrical decoding of vector vortex beams on chip. [PDF]

Sci Adv
Dai M, Zhang X, Chen W, Wang C, Wang Q, Wang QJ.   +5 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

An i-vector backend for speaker verification

Interspeech 2015, 2015
We propose a new approach to the problem of uncertainty modeling in text-dependent speaker verification where speaker factors are used as the feature representation. The state-of-the-art backend in this situation consists in using point estimates of speaker factors to model the joint distribution of pairs of enrollment and test feature vectors under ...
Patrick Kenny, Themos Stafylakis, Md. Jahangir Alam 0001, Marcel Kockmann   +3 more
openaire   +1 more source

Efficient approximated i-vector extraction

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012
I-vectors are currently widely used by state-of-the-art speech processing systems for tasks such as speaker verification and language identification. A shortcoming of i-vector-based systems is that the i-vector extraction process is computationally expensive. In this paper we propose an efficient method to extract i-vectors approximately.
Hagai Aronowitz, Oren Barkan
openaire   +1 more source

Simplification and optimization of i-vector extraction

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
This paper introduces some simplifications to the i-vector speaker recognition systems. I-vector extraction as well as training of the i-vector extractor can be an expensive task both in terms of memory and speed. Under certain assumptions, the formulas for i-vector extraction—also used in i-vector extractor training—can be simplified and lead to a ...
Ondrej Glembek, Lukás Burget, Pavel Matejka, Martin Karafiát, Patrick Kenny   +4 more
openaire   +1 more source

e-vectors: JFA and i-vectors revisited

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017
Systems based on i-vectors represent the current state-of-the-art in text-independent speaker recognition. In this work we introduce a new compact representation of a speech segment, similar to the speaker factors of Joint Factor Analysis (JFA) and to i-vectors, that we call “e-vector”.
CUMANI, SANDRO, LAFACE, Pietro
openaire   +2 more sources

Quasi-Factorial Prior for i-vector Extraction

IEEE Signal Processing Letters, 2015
We analyze the i-vector extraction from the perspective of the prior distribution exerted on the mean supervector of Gaussian mixture model (GMM). To this end, we start off with the analysis of the subspace prior which leads to the compressed representation in the standard i-vector extraction.
Liping Chen, Kong-Aik Lee, Li-Rong Dai 0001, Haizhou Li 0001   +3 more
openaire   +1 more source

Senone I-vectors for robust speaker verification

2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2016
Recent research has shown that using senone posteriors for i-vector extraction can achieve outstanding performance. In this paper, we extend this idea to robust speaker verification by constructing a deep neural network (DNN) comprising a deep belief network (DBN) stacked on top of a denoising autoencoder (DAE).
Zhili Tan, Yingke Zhu, Man-Wai Mak, Brian Kan-Wing Mak   +3 more
openaire   +1 more source

An Investigation on the Use of i-Vectors for Robust ASR

Interspeech 2016, 2016
In this paper we propose two different i-vector representations that improve the noise robustness of automatic speech recognition (ASR). The first kind of i-vectors is derived from ``noise only'' components of speech provided by an adaptive denoising algorithm, the second variant is extracted from mel filterbank energies containing both speech and ...
Dimitrios Dimitriadis, Samuel Thomas 0001, Sriram Ganapathy   +2 more
openaire   +1 more source