Bidirectional Quaternion Long-short Term Memory Recurrent Neural Networks For Speech Recognition

Abstract

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition tasks, due to their efficient representation of long and short term dependencies in sequences of inter-dependent features. Nonetheless, internal dependencies within the element composing multidimensional features are weakly considered by traditional real-valued representations. We propose a novel quaternion long-short term memory (QLSTM) recurrent neural network that takes into account both the external relations between the features composing a sequence, and these internal latent structural dependencies with the quaternion algebra. QLSTMs are compared to LSTMs during a memory copy-task and a realistic application of speech recognition on the Wall Street Journal (WSJ) dataset. QLSTM reaches better performances during the two experiments with up to \(2

Stats

• citations17
• S2 citations—
• github stars0
• HF likes0
• heat score9.41
• arxiv keyparcollet2018bidirectional

Related papers

• Quaternion Recurrent Neural Networks (2018)0.00
• Long Short-term Memory Based Convolutional Recurrent Neural Networks For Large Vocabulary Speech Recognition (2016)6.77
• Memory Visualization For Gated Recurrent Neural Networks In Speech Recognition (2016)11.76
• Lattice Rescoring Strategies For Long Short Term Memory Language Models In Speech Recognition (2017)9.76
• Learning Compact Recurrent Neural Networks (2016)0.00
• A Novel Pyramidal-fsmn Architecture With Lattice-free MMI For Speech Recognition (2018)0.00
• Streaming Multi-speaker ASR With RNN-T (2020)10.07
• High Order Recurrent Neural Networks For Acoustic Modelling (2018)8.60