Results 71 to 80 of about 460,856 (296)

Hyperparameter Optimization of CNN Based Open Set Speaker Verification Using MFCC and Speaker Embedding for Voice Biometric Security

Journal of Applied Informatics and Computing
The development of voice based biometric security systems has increased the demand for authentication methods capable of operating accurately and securely in open set speaker verification scenarios.
Mirza Ardiana, Mat Syai’in, Alief Nur Aisyi Maulidhia, Aulia Rahma Annisa, Yudi Andika, Sholahuddin Muhammad Irsyad, Fauzan Izzul Haq   +6 more
doaj   +1 more source

Unsupervised Learning of Total Variability Embedding for Speaker Verification with Random Digit Strings

Applied Sciences, 2019
Recently, the increasing demand for voice-based authentication systems has encouraged researchers to investigate methods for verifying users with short randomized pass-phrases with constrained vocabulary.
Woo Hyun Kang, Nam Soo Kim
doaj   +1 more source

Bioinspired Adaptive Sensors: A Review on Current Developments in Theory and Application

Advanced Materials, EarlyView.
This review comprehensively summarizes the recent progress in the design and fabrication of sensory‐adaptation‐inspired devices and highlights their valuable applications in electronic skin, wearable electronics, and machine vision. The existing challenges and future directions are addressed in aspects such as device performance optimization ...
Guodong Gong, You Zhou, Qingxiu Li, Wenyu Zhao, Sunyingyue Geng, Hangfei Li, Yan‐Bing Leng, Shirui Zhu, Guanglong Ding, Yongbiao Zhai, Ziyu Lv, Ye Zhou, Su‐Ting Han   +12 more
wiley   +1 more source

Domain-weighted transfer learning and discriminative embeddings for low-resource speaker verification

EURASIP Journal on Audio, Speech, and Music Processing
Transfer learning has been shown to be effective in enhancing speaker verification performance in low-resource conditions. However, the inclusion of additional datasets may cause domain mismatch.
Han Wang, Mingrui He, Mingjun Zhang, Changzhi Luo, Longting Xu   +4 more
doaj   +1 more source

Cosine Scoring with Uncertainty for Neural Speaker Embedding [PDF]

Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to handle ...
Wang, Qiongqiong, Lee, Kong Aik
core   +1 more source

LEAD: Literature Enhanced Ab Initio Discovery of Nitride Dusting Layers for Enhanced Tunnel Magnetoresistance and Lower Resistance Magnetic Tunnel Junctions

Advanced Materials, EarlyView.
Magnetic tunnel junctions (MTJs) using MgO tunnel barriers face challenges of high resistance‐area product and low tunnel magnetoresistance (TMR). To discover alternative materials, Literature Enhanced Ab initio Discovery (LEAD) is developed. The LEAD‐predicted materials are theoretically evaluated, showing that MTJs with dusting of ScN or TiN on ...
Sabiq Islam, William S. Rogers, Chen‐Yu Hu, Ming‐Yuan Song, Xinyu Bao, Shehrin Sayed, Jean Anne C. Incorvia   +6 more
wiley   +1 more source

Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding

IEEE Access
Speaker embeddings trained with Matryoshka Representation Learning (MRL) provide embeddings of various dimensions with minimal overhead, adapting to different computational and storage constraints.
Sunchan Park, Hyung Soon Kim
doaj   +1 more source

Real-time multilingual speech recognition and speaker diarization system based on Whisper segmentation [PDF]

PeerJ Computer Science
This research presents the development of a cutting-edge real-time multilingual speech recognition and speaker diarization system that leverages OpenAI’s Whisper model. The system specifically addresses the challenges of automatic speech recognition (ASR)
Ke-Ming Lyu, Ren-yuan Lyu, Hsien-Tsung Chang   +2 more
doaj   +2 more sources

Improving speaker turn embedding by crossmodal transfer learning from face embedding

, 2017
Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which ...
Le, Nam, Odobez, Jean-Marc, Jean-Marc Odobez, Nam Le   +3 more
core   +1 more source

Neuromorphic Electronics for Intelligence Everywhere: Emerging Devices, Flexible Platforms, and Scalable System Architectures

Advanced Materials, EarlyView.
The perspective presents an integrated view of neuromorphic technologies, from device physics to real‐time applicability, while highlighting the necessity of full‐stack co‐optimization. By outlining practical hardware‐level strategies to exploit device behavior and mitigate non‐idealities, it shows pathways for building efficient, scalable, and ...
Kapil Bhardwaj, Roshni Satheesh Babu, Yuxin Xia, Eva Bestelink, Radu Sporea, Nikos Hastas, Ioannis Zeimpekis, Dimitra G. Georgiadou, Sayani Majumdar   +8 more
wiley   +1 more source