English
Related papers

Related papers: A Comparison of Discrete Latent Variable Models fo…

200 papers

Current self-supervised learning algorithms are often modality-specific and require large amounts of computational resources. To address these issues, we increase the training efficiency of data2vec, a learning objective that generalizes…

Machine Learning · Computer Science 2023-06-16 Alexei Baevski , Arun Babu , Wei-Ning Hsu , Michael Auli

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is…

Computation and Language · Computer Science 2020-02-06 Alexander H. Liu , Tao Tu , Hung-yi Lee , Lin-shan Lee

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

Sound · Computer Science 2021-01-15 Zhiyun Fan , Meng Li , Shiyu Zhou , Bo Xu

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…

Sound · Computer Science 2022-05-09 Nik Vaessen , David A. van Leeuwen

In this paper, we explore the use of a factorized hierarchical variational autoencoder (FHVAE) model to learn an unsupervised latent representation for dialect identification (DID). An FHVAE can learn a latent space that separates the more…

Audio and Speech Processing · Electrical Eng. & Systems 2018-09-13 Suwon Shon , Wei-Ning Hsu , James Glass

In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the…

Sound · Computer Science 2024-02-21 Samir Sadok , Simon Leglaive , Laurent Girin , Xavier Alameda-Pineda , Renaud Séguier

Deep generative models applied to audio have improved by a large margin the state-of-the-art in many speech and music related tasks. However, as raw waveform modelling remains an inherently difficult task, audio generative models are either…

Machine Learning · Computer Science 2021-12-16 Antoine Caillon , Philippe Esling

Existing neural architecture representation learning methods focus on continuous representation learning, typically using Variational Autoencoders (VAEs) to map discrete architectures onto a continuous Gaussian distribution. However,…

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive…

Machine Learning · Computer Science 2021-02-26 Yang Zhao , Ping Yu , Suchismit Mahapatra , Qinliang Su , Changyou Chen

Analyses of self-supervised speech models have begun to reveal where and how they represent different types of information. However, almost all analyses have focused on English. Here, we examine how wav2vec2 models trained on four different…

Computation and Language · Computer Science 2025-06-13 Michele Gubian , Ioana Krehan , Oli Liu , James Kirby , Sharon Goldwater

Recent studies have shown how self-supervised models can produce accurate speech quality predictions. Speech representations generated by the pre-trained wav2vec 2.0 model allows constructing robust predicting models using small amounts of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-06 Helard Becerra , Alessandro Ragano , Andrew Hines

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Computation and Language · Computer Science 2017-11-07 Yu-An Chung , James Glass

Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful representation learning framework that can discover discrete groups of features from a speech signal without supervision. Until now, the VQ-VAE architecture has previously…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yi Zhao , Haoyu Li , Cheng-I Lai , Jennifer Williams , Erica Cooper , Junichi Yamagishi

In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…

Computation and Language · Computer Science 2019-02-15 Ya-Jie Zhang , Shifeng Pan , Lei He , Zhen-Hua Ling

This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…

Computation and Language · Computer Science 2019-06-20 Yu-An Chung , Wei-Ning Hsu , Hao Tang , James Glass

Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec,…

Computation and Language · Computer Science 2024-10-18 Abdul Waheed , Hanin Atwany , Bhiksha Raj , Rita Singh

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

Computation and Language · Computer Science 2019-08-28 Yijun Xiao , William Yang Wang

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Sound · Computer Science 2020-12-18 Mostafa Sadeghi , Simon Leglaive , Xavier Alameda-PIneda , Laurent Girin , Radu Horaud

We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-29 Marco Tagliasacchi , Beat Gfeller , Félix de Chaumont Quitry , Dominik Roblek

Objective speech disorder classification for speakers with communication difficulty is desirable for diagnosis and administering therapy. With the current state of speech technology, it is evident to propose neural networks for this…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Jinzi Qi , Hugo Van hamme