English
Related papers

Related papers: Self-supervised Predictive Coding Models Encode Sp…

200 papers

Learning speaker-specific features is vital in many applications like speaker recognition, diarization and speech recognition. This paper provides a novel approach, we term Neural Predictive Coding (NPC), to learn speaker-specific…

Sound · Computer Science 2019-07-18 Arindam Jati , Panayiotis Georgiou

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Jennifer Williams , Yi Zhao , Erica Cooper , Junichi Yamagishi

The popular frameworks for self-supervised learning of speech representations have largely focused on frame-level masked prediction of speech regions. While this has shown promising downstream task performance for speech recognition and…

Computation and Language · Computer Science 2025-07-22 Varun Krishna , Sriram Ganapathy

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-05 Arsha Nagrani , Joon Son Chung , Samuel Albanie , Andrew Zisserman

Self-supervised models, namely, wav2vec and its variants, have shown promising results in various downstream tasks in the speech domain. However, their inner workings are poorly understood, calling for in-depth analyses on what the model…

Sound · Computer Science 2022-10-28 Kwanghee Choi , Eun Jung Yeo

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…

Sound · Computer Science 2024-06-03 Jungil Kong , Junmo Lee , Jeongmin Kim , Beomjeong Kim , Jihoon Park , Dohee Kong , Changheon Lee , Sangjin Kim

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Sound · Computer Science 2022-10-07 Yehoshua Dissen , Felix Kreuk , Joseph Keshet

In this paper, we propose a new pooling method called spatial pyramid encoding (SPE) to generate speaker embeddings for text-independent speaker verification. We first partition the output feature maps from a deep residual network (ResNet)…

Audio and Speech Processing · Electrical Eng. & Systems 2019-12-30 Youngmoon Jung , Younggwan Kim , Hyungjun Lim , Yeunju Choi , Hoirin Kim

Automatic speaker recognition algorithms typically characterize speech audio using short-term spectral features that encode the physiological and anatomical aspects of speech production. Such algorithms do not fully capitalize on…

Sound · Computer Science 2021-02-16 Anurag Chowdhury , Arun Ross , Prabu David

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-09 Mirco Ravanelli , Yoshua Bengio

Self-supervised speech representations can hugely benefit downstream speech technologies, yet the properties that make them useful are still poorly understood. Two candidate properties related to the geometry of the representation space…

Computation and Language · Computer Science 2024-06-14 Mukhtar Mohamed , Oli Danyi Liu , Hao Tang , Sharon Goldwater

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-02 Jun Wang , Max W. Y. Lam , Dan Su , Dong Yu

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Computation and Language · Computer Science 2024-10-07 Hosein Mohebbi , Grzegorz Chrupała , Willem Zuidema , Afra Alishahi , Ivan Titov

In recent years, the impact of self-supervised speech Transformers has extended to speaker-related applications. However, little research has explored how these models encode speaker information. In this work, we address this gap by…

Computation and Language · Computer Science 2025-06-30 Tzu-Quan Lin , Hsi-Chun Cheng , Hung-yi Lee , Hao Tang

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Saurabhchand Bhati , Jesús Villalba , Piotr Żelasko , Najim Dehak

Cross-lingual alignment in pretrained language models enables knowledge transfer across languages. Similar alignment has been reported in Whisper-style speech encoders, based on spoken translation retrieval using representational…

Computation and Language · Computer Science 2026-04-07 Ryan Soh-Eun Shim , Domenico De Cristofaro , Chengzhi Martin Hu , Alessandro Vietti , Barbara Plank

Speaker embeddings are widely used in speaker verification systems and other applications where it is useful to characterise the voice of a speaker with a fixed-length vector. These embeddings tend to be treated as "black box" encodings,…

Sound · Computer Science 2025-10-21 Mark Huckvale

Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that linear classifiers trained on CPC features can accurately…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-03 Benjamin van Niekerk , Leanne Nortje , Matthew Baas , Herman Kamper