.png){kind=icon}
.png){kind=icon}
Return
Reconstructing Speech From CNN Embeddings
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2021.3073628.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The complete understanding of the decision-making process of Convolutional Neural Networks (CNNs) is far from being fully reached. Many researchers proposed techniques to interpret what a network actually learns from data. Nevertheless many questions still remain unanswered. In this work we study one aspect of this problem by reconstructing speech from the intermediate embeddings computed by a CNNs. Specifically, we consider a pre-trained network that acts as a feature extractor from speech audio. We investigate the possibility of inverting these features, reconstructing the input signals in a black-box scenario, and quantitatively measure the reconstruction quality by measuring the word-error-rate of an off-the-shelf ASR model. Experiments performed using two different CNN architectures trained for six different classification tasks, show that it is possible to reconstruct time-domain speech signals that preserve the semantic content, whenever the embeddings are extracted before the fully connected layers.
Keywords:
Decoding
Task analysis
Spectrogram
Feature extraction
Computer architecture
Image reconstruction
Training
Audio processing
explainable deep learning
speech recognition
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W