Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance

no code implementations • 23 Apr 2024 • Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri

To this end, we propose a novel analysis scheme based on the orthogonal projection-based decomposition of SE errors.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

How does end-to-end speech recognition training impact speech enhancement artifacts?

no code implementations • 20 Nov 2023 • Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri

Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of \emph{processing distortion} generated by single-channel SE on ASR.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR

no code implementations • 18 Jan 2022 • Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri

The artifact component is defined as the SE error signal that cannot be represented as a linear combination of speech and noise sources.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization

no code implementations • 17 Nov 2016 • Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri

We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data.

General Classification Playing the Game of 2048