Acoustic model

An acoustic model is used in Automatic Speech Recognition to represent the relationship between an audio signal and the phonemes or other linguistic… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
Highly Cited
2015
Highly Cited
2015
Standard deep neural network-based acoustic models for automatic speech recognition (ASR) rely on hand-engineered input features… (More)
  • figure 2
  • figure 1
  • figure 4
  • figure 3
  • table 1
Is this relevant?
Highly Cited
2014
Highly Cited
2014
Long Short-Term Memory (LSTM) is a specific recurrent neural network (RNN) architecture that was designed to model temporal… (More)
  • figure 2
  • figure 1
  • table 1
  • figure 3
  • table 2
Is this relevant?
Highly Cited
2013
Highly Cited
2013
Deep neural network acoustic models produce substantial gains in large vocabulary continuous speech recognition systems. Emerging… (More)
  • figure 1
  • table 1
  • figure 2
Is this relevant?
Highly Cited
2012
Highly Cited
2012
We investigate the problem of acoustic modeling in which prior language-specific knowledge and transcribed data are unavailable… (More)
  • figure 1
  • figure 2
  • table 1
  • figure 4
  • table 2
Is this relevant?
Highly Cited
2009
Highly Cited
2009
Acoustic models used in hidden Markov model/neural-network (HMM/NN) speech recognition systems are usually trained with a frame… (More)
  • table 1
  • figure 1
  • table 2
Is this relevant?
Highly Cited
2003
Highly Cited
2003
The performance of speech recognition systems is consistently poor on non-native speech. The challenge for non-native speech… (More)
  • table 1
  • figure 1
  • figure 2
  • figure 3
Is this relevant?
Highly Cited
2002
Highly Cited
2002
This paper describes some recent experiments using unsupervised techniques for acoustic model training in order to reduce the… (More)
  • table 1
  • table 3
  • table 4
  • table 2
Is this relevant?
Highly Cited
2002
Highly Cited
2002
The last decade has witnessed substantial progress in speech recognition technology, with todays state-of-the-art systems being… (More)
Is this relevant?
Highly Cited
2001
Highly Cited
2001
With the distribution of speech technology products all over the world, the portability to new target languages becomes a… (More)
  • table 1
  • table 2
  • figure 1
  • figure 2
  • table 3
Is this relevant?
Highly Cited
2000
Highly Cited
2000
We describe procedures and experimental results using spee ch from diverse source languages to build an ASR system for a single t… (More)
  • table 1
  • table 2
  • table 3
  • table 5
  • table 6
Is this relevant?