paper-with-me

Papers

Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition

2016-09-28 · Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, Shiyue Zhang

Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurrent unit (GRU). However, the dynamic properties behind the remarkable performance remain unclear in many applications, e.g., automatic speech recognition (ASR). This paper employs visualization techniques to study the behavior of LSTM and GRU when performing speech recognition tasks. Our experiments show some interesting patterns in the gated memory, and some of them have inspired simple yet effective modifications on the network structure. We report two of such modifications: (1) lazy cell update in LSTM, and (2) shortcut connections for residual learning. Both modifications lead to more comprehensible and powerful networks.

📄 PDF Abstract BibTeX arXiv:1609.08789

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
GRU A Gated Recurrent Unit, or GRU, is a type of recurrent neural network. It is similar to an LSTM, but only has two gates - a reset…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition

2014-10-16 · Xiangang Li, Xihong Wu

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research…

GPUspeech-recognitionSpeech Recognition

Improving speech recognition by revising gated recurrent units

2017-09-29 · Mirco Ravanelli, Philemon Brakel, Maurizio Omologo, Yoshua Bengio

Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neural Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), whi…

speech-recognitionSpeech Recognition

Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition

2018-11-06 · Titouan Parcollet, Mohamed Morchid, Georges Linarès, Renato de Mori

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 …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

From Nodes to Networks: Evolving Recurrent Neural Networks

2018-03-12 · Aditya Rawal, Risto Miikkulainen

Gated recurrent networks such as those composed of Long Short-Term Memory (LSTM) nodes have recently been used to improve state of the art in many sequential processing tasks such as speech recognition and machine transl…

Language ModelingLanguage ModellingMachine TranslationReinforcement Learning+3

Stabilising and accelerating light gated recurrent units for automatic speech recognition

2023-02-16 · Adel Moumen, Titouan Parcollet

The light gated recurrent units (Li-GRU) is well-known for achieving impressive results in automatic speech recognition (ASR) tasks while being lighter and faster to train than a standard gated recurrent units (GRU). How…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition