paper-with-me

홈 › Papers

Highway Long Short-Term Memory RNNs for Distant Speech Recognition

2015-10-30 · Yu Zhang, Guoguo Chen, Dong Yu, Kaisheng Yao, Sanjeev Khudanpur, James Glass

In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when building deeper LSTMs. We further introduce the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control. Efficient algorithms are proposed to train these novel networks using both frame and sequence discriminative criteria. Experiments on the AMI distant speech recognition (DSR) task indicate that we can train deeper LSTMs and achieve better improvement from sequence training with highway LSTMs (HLSTMs). Our novel model obtains $43.9/47.7\%$ WER on AMI (SDM) dev and eval sets, outperforming all previous works. It beats the strong DNN and DLSTM baselines with $15.7\%$ and $5.3\%$ relative improvement respectively.

📄 PDF Abstract BibTeX arXiv:1510.08983

Code (0)

등록된 구현이 없습니다.

Tasks

Distant Speech Recognitionspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Learning Intrinsic Sparse Structures within Long Short-Term Memory

2017-09-15 · ICLR 2018 1 · Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang 외

Model compression is significant for the wide adoption of Recurrent Neural Networks (RNNs) in both user devices possessing limited resources and business clusters requiring quick responses to large-scale service requests…

Language ModelingLanguage ModellingModel CompressionQuestion Answering

Recurrent Highway Networks with Grouped Auxiliary Memory

2019-12-13 · IEEE Access 2019 12 · Wei Luo ; Feng Yu

Recurrent neural networks (RNNs) are challenging to train, let alone those with deep spatial structures. Architectures built upon highway connections such as Recurrent Highway Network (RHN) were developed to allow larger…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2

Fast Weight Long Short-Term Memory

2018-04-18 · T. Anderson Keller, Sharath Nittur Sridhar, Xin Wang

Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to…

Retrieval

Learning Over Long Time Lags

2016-02-13 · Hojjat Salehinejad

The advantage of recurrent neural networks (RNNs) in learning dependencies between time-series data has distinguished RNNs from other deep learning models. Recently, many advances are proposed in this emerging field. How…

Time SeriesTime Series Analysis

X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction

2025-10-31 · Aanchal Rajesh Chugh, Marion Neumeier, Sebastian Dorn arxiv

Accurate trajectory prediction is crucial for safe and reliable autonomous driving systems, requiring models that capture long-term temporal dependencies while accounting for social interactions among neighboring vehicle…

Trajectory PredictionAutonomous Driving