End-to-end Attention-based Distant Speech Recognition With Highway LSTM

Abstract

End-to-end attention-based models have been shown to be competitive alternatives to conventional DNN-HMM models in the Speech Recognition Systems. In this paper, we extend existing end-to-end attention-based models that can be applied for Distant Speech Recognition (DSR) task. Specifically, we propose an end-to-end attention-based speech recognizer with multichannel input that performs sequence prediction directly at the character level. To gain a better performance, we also incorporate Highway long short-term memory (HLSTM) which outperforms previous models on AMI distant speech recognition task.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytaherian2016end

Related papers

• Language Modeling With Highway LSTM (2017)10.21
• A Comparison Of End-to-end Models For Long-form Speech Recognition (2019)12.93
• On Using 2D Sequence-to-sequence Models For Speech Recognition (2019)0.00
• An Online Attention-based Model For Speech Recognition (2018)9.59
• Improving Hybrid Ctc/attention End-to-end Speech Recognition With Pretrained Acoustic And Language Model (2021)8.82
• Audio-attention Discriminative Language Model For ASR Rescoring (2019)9.23
• Streaming Attention-based Models With Augmented Memory For End-to-end Speech Recognition (2020)5.84
• Transformer-based End-to-end Speech Recognition With Local Dense Synthesizer Attention (2020)12.04