Papers › Unsupervised speech representation learning using WaveNet autoencoders

Unsupervised speech representation learning using WaveNet autoencoders

25 Jan 2019arXiv:1901.08810archive 2025-07-28

Jan Chorowski, Ron J. Weiss, Samy Bengio, Aäron van den Oord

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content from the signal, e.g. phoneme identities, while being invariant to confounding low level details in the signal such as the underlying pitch contour or background noise. Since the learned representation is tuned to contain only phonetic content, we resort to using a high capacity WaveNet decoder to infer information discarded by the encoder from previous samples. Moreover, the behavior of autoencoder models depends on the kind of constraint that is applied to the latent representation. We compare three variants: a simple dimensionality reduction bottleneck, a Gaussian Variational Autoencoder (VAE), and a discrete Vector Quantized VAE (VQ-VAE). We analyze the quality of learned representations in terms of speaker independence, the ability to predict phonetic content, and the ability to accurately reconstruct individual spectrogram frames. Moreover, for discrete encodings extracted using the VQ-VAE, we measure the ease of mapping them to phonemes. We introduce a regularization scheme that forces the representations to focus on the phonetic content of the utterance and report performance comparable with the top entries in the ZeroSpeech 2017 unsupervised acoustic unit discovery task.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

MingjieChen/wavenet_autoencoders mentioned on GitHubpytorchSyntology: not harvested report
StanislavParovoy/VQ-VAE-WaveNet mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
bshall/ZeroSpeech mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
hrbigelow/ae-wavenet mentioned on GitHubpytorchSyntology: not harvested report
swasun/VQ-VAE-Speech mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to WaveNet: A Generative Model for Raw Audio (arXiv:1609.03499; that paper's own run record: 65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified) and Neural Discrete Representation Learning (arXiv:1711.00937; that paper's own run record: 64 ran (of which 35 constructed an object rather than computing a result; 60 with no instrument failure: 0 honoured, 0 violated, 60 with no contract checked; 4 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderDimensionality ReductionRepresentation LearningSpeech Representation Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dilated Causal ConvolutionMixture of Logistic DistributionsVQ-VAEWaveNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections