TIMIT

TIMIT is a corpus of phonemically and lexically transcribed speech of American English speakers of different sexes and dialects. Each transcribed… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2014
Highly Cited
2014
Despite their theoretical appeal and grounding in tractable convex optimization techniques, kernel methods are often not the… (More)
  • table 2
  • table 3
  • table 1
Is this relevant?
Highly Cited
2013
Highly Cited
2013
Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist… (More)
  • figure 1
  • figure 3
Is this relevant?
Highly Cited
2013
Highly Cited
2013
Deep Bidirectional LSTM (DBLSTM) recurrent neural networks have recently been shown to give state-of-the-art performance on the… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
Is this relevant?
Highly Cited
2012
Highly Cited
2012
In the information age, computer applications have become part of modern life and this has in turn encouraged the expectations of… (More)
  • table 1
  • table 2
  • table 4
  • table 5
  • table 6
Is this relevant?
Highly Cited
2012
Highly Cited
2012
Gaussian mixture models are currently the dominant technique for modeling the emission distribution of hidden Markov models for… (More)
  • figure 2
  • figure 1
  • figure 3
  • figure 4
  • figure 7
Is this relevant?
Highly Cited
2011
Highly Cited
2011
The use of exemplar-based methods, such as support vector machines (SVMs), k-nearest neighbors (kNNs) and sparse representations… (More)
  • figure 3
  • figure 1
  • figure 4
  • table II
  • table V
Is this relevant?
2010
2010
The QUT-NOISE-TIMIT corpus consists of 600 hours of noisy speech sequences designed to enable a thorough evaluation of voice… (More)
  • figure 1
  • figure 2
Is this relevant?
2008
2008
We compare the performance of a recurrent neural network with the best results published so far on phoneme recognition in the… (More)
  • table 1
Is this relevant?
Highly Cited
2006
Highly Cited
2006
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
Is this relevant?