CoChat

Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR

Open access
Swietojanski, Pawel, Ghoshal, Arnab, Renals, Steve · 2012 · 2012 IEEE Spoken Language Technology Workshop (SLT)
Cited by 108

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Abstract

We investigate the use of cross-lingual acoustic data to initialise deep neural network (DNN) acoustic models by means of unsupervised restricted Boltzmann machine (RBM) pre-training. DNNs for German are pretrained using one or all of German, Portuguese, Spanish and Swedish. The DNNs are used in a tandem configuration, where the network outputs are used as features for a hidden Markov model (HMM) whose emission densities are modeled by Gaussian mixture models (GMMs), as well as in a hybrid configuration, where the network outputs are used as the HMM state likelihoods. The experiments show that unsupervised pretraining is more crucial for the hybrid setups, particularly with limited amounts of transcribed training data. More importantly, unsupervised pretraining is shown to be language-independent.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/slt.2012.6424230

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

  • Greedy layer-wise training of deep networks

    Bengio, Y., Lamblin, P., Popovici, D., & Larochelle, H. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0024 · Cited by 4,841 · cited 2×

    “It is possible, even likely, that this characteristic will be demonstrated by other unsupervised pretraining techniques as well, for example, pretraining using stacked autoencoders [20] While pretraining is seen to be language-independent, no clear pattern emerges when going from 15 to 85 hours of data for pretraining.”
  • Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition

    Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2134090 · Cited by 3,011 · cited 2×

    “For our investigation of unsupervised cross-lingual pretraining, RBMs were a natural first choice due to their previous successful application in speech recognition [15, 16].”

Cited by

See all 108

Metadata

Authors
Swietojanski, P., Ghoshal, A., & Renals, S.
Venue
2012 IEEE Spoken Language Technology Workshop (SLT)
Publisher
IEEE
Published
2012-12
Pages
246-251
OpenAlex
W2120209245
Cited by
108
References
2
FWCI
12.31
Type
conference paper
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.