Encrypted Speech Recognition using Deep Polynomial Networks
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in cloud may also reveal some sensitive information. This paper proposes a deep polynomial network (DPN) that can be applied to the encrypted speech as an acoustic model. It allows clients to send their data in an encrypted form to the cloud to ensure that their data remains confidential, at mean while the DPN can still make frame-level predictions over the encrypted speech and return them in encrypted form. One good property of the DPN is that it can be trained on unencrypted speech features in the traditional way. To keep the cloud away from the raw audio and recognition results, a cloud-local joint decoding framework is also proposed. We demonstrate the effectiveness of model and framework on the Switchboard and Cortana voice assistant tasks with small performance degradation and latency increased comparing with the traditional cloud-based DNNs.
Code (0)
등록된 구현이 없습니다.
Tasks
speech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
A privacy-preserving method using secret key for convolutional neural network-based speech classification
In this paper, we propose a privacy-preserving method with a secret key for convolutional neural network (CNN)-based speech classification tasks. Recently, many methods related to privacy preservation have been developed…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Classificationimage-classification+5Encrypted Simultaneous Control of Joint Angle and Stiffness of Antagonistic Pneumatic Artificial Muscle Actuator by Polynomial Approximation
This study proposes an encrypted simultaneous control system for an antagonistic pneumatic artificial muscle (PAM) actuator toward developing a cybersecure and flexible actuator. First, a novel simultaneous control syste…
Public-Decay Homomorphic State Space Models for Private Sequence Inference
Fully homomorphic encryption (FHE) changes sequence-model design because rotations, encrypted products, ciphertext materialization, multiplicative depth, and bootstrapping pressure can dominate ordinary neural-network co…
Ring-LWE based encrypted controller with unlimited number of recursive multiplications and effect of error growth
In this paper, we propose an encrypted dynamic controller that executes an unlimited number of recursive homomorphic multiplications on a Ring Learning With Errors (Ring-LWE) based cryptosystem without bootstrapping. The…
CryptoDL: Deep Neural Networks over Encrypted Data
Machine learning algorithms based on deep neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which i…
Optical Character RecognitionOptical Character Recognition (OCR)Privacy Preserving