Encoder-decoder With Focus-mechanism For Sequence Labelling Based Spoken Language Understanding

Abstract

This paper investigates the framework of encoder-decoder with attention for sequence labelling based spoken language understanding. We introduce Bidirectional Long Short Term Memory - Long Short Term Memory networks (BLSTM-LSTM) as the encoder-decoder model to fully utilize the power of deep learning. In the sequence labelling task, the input and output sequences are aligned word by word, while the attention mechanism cannot provide the exact alignment. To address this limitation, we propose a novel focus mechanism for encoder-decoder framework. Experiments on the standard ATIS dataset showed that BLSTM-LSTM with focus mechanism defined the new state-of-the-art by outperforming standard BLSTM and attention based encoder-decoder. Further experiments also show that the proposed model is more robust to speech recognition errors.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhu2016encoder

Related papers

• State-of-the-art Speech Recognition With Sequence-to-sequence Models (2017)21.01
• Full Attention Bidirectional Deep Learning Structure For Single Channel Speech Enhancement (2021)0.00
• Towards Better Decoding And Language Model Integration In Sequence To Sequence Models (2016)15.67
• Supervised Attention In Sequence-to-sequence Models For Speech Recognition (2022)5.84
• Joint Ctc-attention Based End-to-end Speech Recognition Using Multi-task Learning (2016)20.43
• Utterance-level End-to-end Language Identification Using Attention-based CNN-BLSTM (2019)11.67
• Optimizing Alignment Of Speech And Language Latent Spaces For End-to-end Speech Recognition And Understanding (2021)9.03
• Improving Speech Emotion Recognition Through Focus And Calibration Attention Mechanisms (2022)0.00