Concepedia

Takafumi Koshinaka

TK

Statistics

Publications

17

Citations

847

H-Index

13

Active since

2009

Affiliations

NEC (Japan)(Current)

Tokyo Institute of Technology

Institute for Infocomm Research

Yokohama City University

Agency for Science, Technology and Research

Takafumi Koshinaka is an author at NEC (Japan) specializing in speech recognition, computing, and speaker recognition.

Publications per year

2009–2023

17

Publications

17

Attentive Statistics Pooling for Deep Speaker Embedding

Koji Okabe, Takafumi Koshinaka, Koichi Shinoda · 2018 · 509 citations · Full text

Computing, Computer Science, Feature Engineering +13

Speaker Augmentation and Bandwidth Extension for Deep Speaker Embedding

H. Yamamoto, Kong Aik Lee, Koji Okabe et al. · 2019 · 58 citations

Computing, Speech-language Pathology, Acoustics +9

Fast and accurate personal authentication using ear acoustics

Takayuki Arakawa, Takafumi Koshinaka, Shohei Yano et al. · 2016 · 33 citations

Computing, Otolaryngology, Acoustics +12

Xi-Vector Embedding for Speaker Recognition

Kong Aik Lee, Qiongqiong Wang, Takafumi Koshinaka · IEEE Signal Processing Letters · 2021 · 29 citations

Computing, Computer Science, Machine Learning +11

i-Vector Transformation Using a Novel Discriminative Denoising Autoencoder for Noise-Robust Speaker Recognition

Shivangi Mahto, H. Yamamoto, Takafumi Koshinaka · 2017 · 26 citations

Computing, Computational Engineering, Acoustics +14

1–5 of 17