Investigating Bidirectional Recurrent Neural Network Language Models for Speech Recognition
Explore this paper's citation graph
Summary
The issues of training bidirectional recurrent neural network language models (bi-RNNLMs) for speech recognition are examined and a probability smoothing technique is proposed, that addresses the very sharp posteriors that are often observed in these models.
- Type
- article
- Published
- 2017-08-20
- Cited by
- 44
- References
- 23
- Access
- Open access
- OpenAlex
- https://openalex.org/W2747917286
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:1131372
Keywords
Computer science, Recurrent neural network, Speech recognition, Time delay neural network, Language model
References
- Log-linear interpolation of language models
- Recurrent neural network based language model
- Long Short-Term Memory
- Two decades of statistical language modeling: where do we go from here?
- Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling
- Bidirectional recurrent neural networks
- A survey on the application of recurrent neural networks to statistical language modeling
- Bidirectional recurrent neural network language models for automatic speech recognition
- Extensions of recurrent neural network language model
- Fast and Robust Neural Network Joint Models for Statistical Machine Translation
- On training bi-directional neural network language model with noise contrastive estimation
- Investigation of back-off based interpolation between recurrent neural network and n-gram language models
- Recurrent Neural Network Based Language Modeling in Meeting Recognition
- Long short-term memory recurrent neural network architectures for large scale acoustic modeling
- Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models
- Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages
- CUED-RNNLM — An open-source toolkit for efficient training and evaluation of recurrent neural network language models
- LSTM Neural Networks for Language Modeling
- Exploiting the succeeding words in recurrent neural network language models
- Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition
Cited by
- Recurrent Neural Network Language Model Adaptation for Conversational Speech Recognition
- Investigation on Estimation of Sentence Probability by Combining Forward, Backward and Bi-directional LSTM-RNNs
- Active Memory Networks for Language Modeling
- Advances in Low Resource ASR: A Deep Learning Perspective
- Multiple beamformers with ROVER for the CHiME-5 Challenge
- Persian Language Modeling Using Recurrent Neural Networks
- Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features
- Improvements to N-gram Language Model Using Text Generated from Neural Language Model
- Effective Sentence Scoring Method using Bidirectional Language Model for Speech Recognition
- Exploiting Future Word Contexts in Neural Network Language Models for Speech Recognition
- On the use of prior and external knowledge in neural sequence models
- Future word contexts in neural network language models
- Improved Training Of Neural Trans-Dimensional Random field Language Models with Dynamic Noise-Contrastive Estimation
- Improved Deep Duel Model for Rescoring N-Best Speech Recognition List Using Backward LSTMLM and Ensemble Encoders
- Pseudolikelihood Reranking with Masked Language Models
- Effective Sentence Scoring Method Using BERT for Speech Recognition
- Language Modeling Using Part-of-speech and Long Short-Term Memory Networks
- Generalized Large-Context Language Models Based on Forward-Backward Hierarchical Recurrent Encoder-Decoder Models
- Finnish Language Modeling with Deep Transformer Models
- Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
Related papers
- Pattern classification by assembling small neural networks
- Bidirectional recurrent neural network language models for automatic speech recognition
- A new recurrent neural network architecture for pattern recognition
- The research of digital recognition technology based on bp neural network
- 2010 Special Issue: Classification of 2-dimensional array patterns: Assembling many small neural networks is better than using a large one
- Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks
- Artificial Neural Networks For Pattern Recognize Handwritten
- New Neural Network Model for Pattern Recognition