paper-with-me

홈 › Papers

Privacy-Preserving Speech Representation Learning using Vector Quantization

2022-03-15 · Pierre Champion, Denis Jouvet, Anthony Larcher

With the popularity of virtual assistants (e.g., Siri, Alexa), the use of speech recognition is now becoming more and more widespread.However, speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns.The presented experiments show that the representations extracted by the deep layers of speech recognition networks contain speaker information.This paper aims to produce an anonymous representation while preserving speech recognition performance.To this end, we propose to use vector quantization to constrain the representation space and induce the network to suppress the speaker identity.The choice of the quantization dictionary size allows to configure the trade-off between utility (speech recognition) and privacy (speaker identity concealment).

📄 PDF Abstract BibTeX arXiv:2203.09518

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy PreservingQuantizationRepresentation Learningspeech-recognitionSpeech RecognitionSpeech Representation Learning

Similar Papers 제목 키워드 기반

Are disentangled representations all you need to build speaker anonymization systems?

2022-08-22 · Pierre Champion, Denis Jouvet, Anthony Larcher

Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to transform a speech signal to remove the s…

AllAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Disentanglement+5

DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector Quantization

2020-12-11 · Shaoshi Ling, Yuzong Liu

Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-super…

DiversityQuantizationRepresentation Learningspeech-recognition+2

Universal Semantic Disentangled Privacy-preserving Speech Representation Learning

2025-05-19 · Biel Tura Vecino, Subhadeep Maji, Aravind Varier, Antonio Bonafonte 외

The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training data. In this study, we propose a speake…

DecoderPrivacy PreservingRepresentation LearningSpeaker anonymization+1

Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge

2020-05-19 · Benjamin van Niekerk, Leanne Nortje, Herman Kamper

In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic content from speaker-specific details. We p…

Acoustic Unit DiscoveryVoice Conversion

Speech Tokenizer is Key to Consistent Representation

2025-07-09 · Wonjin Jung, Sungil Kang, Dong-Yeon Cho arxiv

Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel speech tokenizer with broad applicabili…

Emotion RecognitionVoice Conversion