1 code implementation • 5 Apr 2024 • Krishna Subramani, Paris Smaragdis, Takuya Higuchi, Mehrez Souden
Non-negative Matrix Factorization (NMF) is a powerful technique for analyzing regularly-sampled data, i. e., data that can be stored in a matrix.
2 code implementations • 30 Jan 2024 • Jee-weon Jung, Wangyou Zhang, Jiatong Shi, Zakaria Aldeneh, Takuya Higuchi, Barry-John Theobald, Ahmed Hussen Abdelaziz, Shinji Watanabe
First, we provide an open-source platform for researchers in the speaker recognition community to effortlessly build models.
Ranked #1 on Speaker Verification on VoxCeleb (using extra training data)
no code implementations • 27 Sep 2023 • Avamarie Brueggeman, Takuya Higuchi, Masood Delfarah, Stephen Shum, Vineet Garg
Our investigation reveals that SE can improve KWS accuracy on noisy speech when the backend model is trained on clean speech; however, despite our extensive exploration, it is difficult to improve the KWS accuracy with SE when the backend is trained on noisy speech.
no code implementations • 27 Sep 2023 • Takuya Higuchi, Avamarie Brueggeman, Masood Delfarah, Stephen Shum
Voice triggering (VT) enables users to activate their devices by just speaking a trigger phrase.
no code implementations • 5 Apr 2022 • Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed Tewfik
A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task.
no code implementations • 15 Jul 2021 • Takuya Higuchi, Anmol Gupta, Chandra Dhir
In this approach, an output of an acoustic model is split into two branches for the two tasks, one for phoneme transcription trained with the ASR data and one for keyword classification trained with the KWS data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 18 Feb 2021 • Takuya Higuchi, Shreyas Saxena, Mehrez Souden, Tien Dung Tran, Masood Delfarah, Chandra Dhir
We propose dynamic curriculum learning via data parameters for noise robust keyword spotting.