Language Modeling With Highway LSTM

Abstract

Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM (HW-LSTM) model for language modeling. The added highway networks increase the depth in the time dimension. Since a typical LSTM has two internal states, a memory cell and a hidden state, we compare various types of HW-LSTM by adding highway networks onto the memory cell and/or the hidden state. Experimental results on English broadcast news and conversational telephone speech recognition show that the proposed HW-LSTM LM improves speech recognition accuracy on top of a strong LSTM LM baseline. We report 5.1% and 9.9% on the Switchboard and CallHome subsets of the Hub5 2000 evaluation, which reaches the best performance numbers reported on these tasks to date.

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keykurata2017language

Related papers

• End-to-end Attention-based Distant Speech Recognition With Highway LSTM (2016)0.00
• Full-sum Decoding For Hybrid HMM Based Speech Recognition Using LSTM Language Model (2020)0.00
• Transformer Language Models With Lstm-based Cross-utterance Information Representation (2021)10.48
• Lattice Rescoring Strategies For Long Short Term Memory Language Models In Speech Recognition (2017)9.76
• LSTM-LM With Long-term History For First-pass Decoding In Conversational Speech Recognition (2020)0.00
• Towards Language Modelling In The Speech Domain Using Sub-word Linguistic Units (2021)0.00
• Recent Advances In Speech Language Models: A Survey (2024)14.64
• Memory Augmented Lookup Dictionary Based Language Modeling For Automatic Speech Recognition (2022)0.00