Results 11 to 20 of about 16,736,389 (319)

Integrate deep neural network and support vector machine to improve the quality of voice processing in Internet of Things devices

Tạp chí Khoa học, 2023
Along with the development of science and technology, especially internet of things (IOT), IOT-related products increasingly contribute to improving people’s life.
NGUYEN Nang An, TRAN Thanh Trung, TRAN Kim Hoan, NGUYEN Tuan Anh, PHAM Minh Doanh   +4 more
doaj   +1 more source

The XMUSPEECH System for Accented English Automatic Speech Recognition

Applied Sciences, 2022
In this paper, we present the XMUSPEECH systems for Track 2 of the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC2020). Track 2 is an Automatic Speech Recognition (ASR) task where the non-native English speakers have various ...
Fuchuan Tong, Tao Li, Dexin Liao, Shipeng Xia, Song Li, Qingyang Hong, Lin Li   +6 more
doaj   +1 more source

Block-wise training for i-vector [PDF]

2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP), 2014
We propose a fast block-wise and parallel training approach to train i-vector systems. This approach divides the loading matrix into groups according to components or acoustic feature dimensions and trains the loading matrices of these groups independently and in parallel.
Fanhu Bie, Jun Wang 0073, Dong Wang 0013, Thomas Fang Zheng   +3 more
openaire   +1 more source

Neural i-vectors

The Speaker and Language Recognition Workshop (Odyssey 2020), 2020
Accepted to Odyssey 2020: The Speaker and Language Recognition Workshop. Version 2 (bugfix)
Vestman, Ville, Lee, Kong Aik, Kinnunen, Tomi   +2 more
openaire   +4 more sources

Automatic Language Identification Using Speech Rhythm Features for Multi-Lingual Speech Recognition

Applied Sciences, 2020
The conventional speech recognition systems can handle the input speech of a specific single language. To realize multi-lingual speech recognition, a language should be firstly identified from input speech.
Hwamin Kim, Jeong-Sik Park
doaj   +1 more source

Identity Vector Extraction by Perceptual Wavelet Packet Entropy and Convolutional Neural Network for Voice Authentication

Entropy, 2018
Recently, the accuracy of voice authentication system has increased significantly due to the successful application of the identity vector (i-vector) model. This paper proposes a new method for i-vector extraction.
Lei Lei, Kun She
doaj   +1 more source

Speech Replay Spoofing Attack Detection System Based on Fusion of Classification Algorithms

Известия Алтайского государственного университета, 2018
Fast development of modern technologies of digital processing and speech recording leads to the fact that it is necessary to take into account the potential threats from the speech replay attacks.
А.А. Лепендин, Я.А. Филин, П.В. Малинин   +2 more
doaj   +1 more source

A cross-sectional study to ascertain malaria prevalence among asymptomatic travellers arriving on the Lihir Group of Islands, Papua New Guinea: implications for elimination efforts

Malaria Journal, 2023
Background The Lihir Islands of Papua New Guinea host a mining operation that has resulted in a mine-impacted zone (MIZ) with reduced malaria transmission and a substantial influx of mine employees, informal cross-country traders, returning locals, and ...
Pere Millat-Martínez, Bàrbara Baro, Bernadine Kasian, Lina Lorry, Sergi Sanz, Chilaka Wali, Sylvia Raulo, Arthur Elizah, Tamarah Koleala, Maria Kaius-Ome, Stephan Karl, Oriol Mitjà, Moses Laman, William Pomat, Quique Bassat   +14 more
doaj   +1 more source

M-Hazy Vector Spaces over M-Hazy Field

Mathematics, 2021
The generalization of binary operation in the classical algebra to fuzzy binary operation is an important development in the field of fuzzy algebra. The paper proposes a new generalization of vector spaces over field, which is called M-hazy vector spaces
Faisal Mehmood, Fu-Gui Shi
doaj   +1 more source

Language-depedent I-Vectors for LRE15

CoRR, 2017
A standard recipe for spoken language recognition is to apply a Gaussian back-end to i-vectors. This ignores the uncertainty in the i-vector extraction, which could be important especially for short utterances. A recent paper by Cumani, Plchot and Fer proposes a solution to propagate that uncertainty into the backend.
Niko Brümmer, Albert Swart
openaire   +2 more sources