Corpus ID: 16300834

Recognition of spontaneous conversational speech using long short-term memory phoneme predictions

@inproceedings{Wllmer2010RecognitionOS,
  title={Recognition of spontaneous conversational speech using long short-term memory phoneme predictions},
  author={M. W{\"o}llmer and F. Eyben and B. Schuller and G. Rigoll},
  booktitle={INTERSPEECH},
  year={2010}
}
We present a novel continuous speech recognition framework designed to unite the principles of triphone and Long ShortTerm Memory (LSTM) modeling. The LSTM principle allows a recurrent neural network to store and to retrieve information over long time periods, which was shown to be well-suited for the modeling of co-articulation effects in human speech. Our system uses a bidirectional LSTM network to generate a phoneme prediction feature that is observed by a triphone-based large-vocabulary… Expand
21 Citations
A novel bottleneck-BLSTM front-end for feature-level context modeling in conversational speech recognition
  • 14
A multi-stream ASR framework for BLSTM modeling of conversational speech
  • 45
  • PDF
Feature Frame Stacking in RNN-Based Tandem ASR Systems - Learned vs. Predefined Context
  • 13
  • PDF
Enhancing Spontaneous Speech Recognition with BLSTM Features
  • 7
Localization of non-linguistic events in spontaneous speech by Non-Negative Matrix Factorization and Long Short-Term Memory
  • 28
  • PDF
Probabilistic asr feature extraction applying context-sensitive connectionist temporal classification networks
  • 4
  • PDF
Feature combination and stacking of recurrent and non-recurrent neural networks for LVCSR
  • 21
  • Highly Influenced
  • PDF
Computational Assessment of Interest in Speech—Facing the Real-Life Challenge
  • 5
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 24 REFERENCES
Tandem acoustic modeling in large-vocabulary recognition
  • D. Ellis, R. Singh, Sunil Sivadas
  • Computer Science
  • 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
  • 2001
  • 94
  • PDF
Robust in-car spelling recognition - a tandem BLSTM-HMM approach
  • 23
  • PDF
Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks
  • 66
  • PDF
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
  • 2,510
  • PDF
A Tandem BLSTM-DBN Architecture for Keyword Spotting with Enhanced Context Modeling
  • 21
  • PDF
Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition
  • 448
  • PDF
Bidirectional LSTM Networks for Context-Sensitive Keyword Detection in a Cognitive Virtual Agent Framework
  • 63
  • PDF
Enhanced Phone Posteriors for Improving Speech Recognition Systems
  • 41
  • PDF
Combining Long Short-Term Memory and Dynamic Bayesian Networks for Incremental Emotion-Sensitive Artificial Listening
  • 146
  • PDF
MMIE training of large vocabulary recognition systems
  • 211
...
1
2
3
...