paper-with-me

Papers

Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling

2024-04-01 · Injune Hwang, Kyogu Lee

Recently, there have been efforts to encode the linguistic information of speech using a self-supervised framework for speech synthesis. However, predicting representations from surrounding representations can inadvertently entangle speaker information in the speech representation. This paper aims to remove speaker information by exploiting the structured nature of speech, composed of discrete units like phonemes with clear boundaries. A neural network predicts these boundaries, enabling variable-length pooling for event-based representation extraction instead of fixed-rate methods. The boundary predictor outputs a probability for the boundary between 0 and 1, making pooling soft. The model is trained to minimize the difference with the pooled representation of the data augmented by time-stretch and pitch-shift. To confirm that the learned representation includes contents information but is independent of speaker information, the model was evaluated with libri-light's phonetic ABX task and SUPERB's speaker identification task.

📄 PDF Abstract BibTeX arXiv:2404.00856

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker IdentificationSpeech Synthesis

Similar Papers 제목 키워드 기반

Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation

2025-05-25 · Giuseppe Ruggiero, Matteo Testa, Jurgen Van de Walle, Luigi di Caro

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content …

DisentanglementSelf-Supervised LearningVoice Conversion

ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers

2022-04-20 · Kaizhi Qian, Yang Zhang, Heting Gao, Junrui Ni 외

Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of th…

DisentanglementSelf-Supervised Learning

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

Unsupervised Learning of Disentangled Speech Content and Style Representation

2020-10-24 · Andros Tjandra, Ruoming Pang, Yu Zhang, Shigeki Karita

We present an approach for unsupervised learning of speech representation disentangling contents and styles. Our model consists of: (1) a local encoder that captures per-frame information; (2) a global encoder that captu…

DecoderSpeaker Recognition

Learning task-specific subspaces via interventional post-training of speech foundation models

2026-06-16 · Jack Cox, Jon Barker arxiv

Speech foundation models, pre-trained on large corpora of unlabelled speech data, produce general-purpose representations which are useful across tasks. However, these representations encode information about salient spe…

Contrastive LearningSpeaker VerificationKeyword Spotting