Skip to search formSkip to main contentSkip to account menu

AST: Audio Spectrogram Transformer

The Audio Spectrogram Transformer (AST) is introduced, the first convolution-free, purely attention-based model for audio classification, and an approach to transfer knowledge from ImageNet pretrained ViT to AST is proposed.
View PDF on arXiv (opens in a new tab)

Speech database development at MIT: Timit and beyond

View via Publisher (opens in a new tab)

Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams

An unsupervised learning framework is presented to address the problem of detecting spoken keywords by using segmental dynamic time warping to compare the Gaussian posteriorgrams between keyword samples and test utterances and obtaining the keyword detection result.
View on IEEE (opens in a new tab)

An Unsupervised Autoregressive Model for Speech Representation Learning

Speech representations learned by the proposed unsupervised autoregressive neural model significantly improve performance on both phone classification and speaker verification over the surface features and other supervised and unsuper supervised approaches.
View PDF on arXiv (opens in a new tab)

Unsupervised Pattern Discovery in Speech

It is shown how pattern discovery can be used to automatically acquire lexical entities directly from an untranscribed audio stream by exploiting the structure of repeating patterns within the speech signal.
View on IEEE (opens in a new tab)

Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data

A factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision by formulating it explicitly within a factorsized hierarchical graphical model that imposes sequence-dependent priors and sequence-independent priors to different sets of latent variables.
View PDF on arXiv (opens in a new tab)

A probabilistic framework for segment-based speech recognition

  • James R. Glass
  • Computer Science
    Computer Speech and Language
  • 1 April 2003
View via Publisher (opens in a new tab)

Highway long short-term memory RNNS for distant speech recognition

This paper extends the deep long short-term memory (DL-STM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers, and introduces the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control.
View on IEEE (opens in a new tab)

What do Neural Machine Translation Models Learn about Morphology?

This work analyzes the representations learned by neural MT models at various levels of granularity and empirically evaluates the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks.
View on ACL (opens in a new tab)

Unsupervised Learning of Spoken Language with Visual Context

A deep neural network model capable of rudimentary spoken language acquisition using untranscribed audio training data, whose only supervision comes in the form of contextually relevant visual images, is presented.
View Paper (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)