Results 1 to 10 of about 5,064 (117)
Disentangled Speaker and Nuisance Attribute Embedding for Robust Speaker Verification
IEEE Access, 2020 Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based methods are known to
Woo Hyun Kang, Min Hyun Han
exaly +3 more sources
Applied Sciences (Switzerland)Automatic speech recognition (ASR) aims at understanding naturally spoken human speech to be used as text inputs to machines. In multi-speaker environments, where multiple speakers are talking simultaneously with a large amount of overlap, a significant ...
Gil-Jin Jang
exaly +3 more sources
Design and Efficacy of a Speaker Verification Method Combining CNN and Transformer for Secure Access Control [PDF]
SensorsIn the rapidly evolving landscape of computer and mobile applications, the demand for secure access control has become increasingly pivotal. This paper introduces a speaker verification method aimed at remotely verifying an individual’s claimed identity,
Xiao Li, Xiao Hu, Kun Niu, Ling Tuo
doaj +2 more sources
Frontiers in Artificial Intelligence, 2023 Modeling virtual agents with behavior style is one factor for personalizing human-agent interaction. We propose an efficient yet effective machine learning approach to synthesize gestures driven by prosodic features and text in the style of different ...
Mireille Fares +2 more
doaj +1 more source
Residual Information in Deep Speaker Embedding Architectures
Mathematics, 2022 Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone.
Adriana Stan
doaj +1 more source
IEEE Access, 2021 This paper proposes a non-parallel cross-lingual voice conversion (CLVC) model that can mimic voice while continuously controlling speaker individuality on the basis of the variational autoencoder (VAE) and star generative adversarial network (StarGAN ...
Tuan Vu Ho, Masato Akagi
doaj +1 more source
Speaker/Style-Dependent Neural Network Speech Synthesis Based on Speaker/Style Embedding [PDF]
Journal of Universal Computer Science, 2020 The paper presents a novel architecture and method for training neural networks to produce synthesized speech in a particular voice and speaking style, based on a small quantity of target speaker/style training data. The method is based on neural network
Milan Sečujski +4 more
doaj +3 more sources
U-Vectors: Generating Clusterable Speaker Embedding from Unlabeled Data
Applied Sciences, 2021 Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the classification task.
Muhammad Firoz Mridha +5 more
doaj +1 more source
IEEE Access, 2021 In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding training in the back-
Sung Hwan Mun +4 more
doaj +1 more source
Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection
IEEE Access, 2023 Automatic speech recognition of a target speaker in the presence of interfering speakers remains a challenging issue. One approach to tackle this problem is target-speaker speech recognition, which conditions the recognition process on an embedding that ...
Takafumi Moriya +4 more
doaj +1 more source