paper-with-me

홈 › Papers

An Improved Residual LSTM Architecture for Acoustic Modeling

2017-08-17 · Lu Huang, Jiasong Sun, Ji Xu, Yi Yang

Long Short-Term Memory (LSTM) is the primary recurrent neural networks architecture for acoustic modeling in automatic speech recognition systems. Residual learning is an efficient method to help neural networks converge easier and faster. In this paper, we propose several types of residual LSTM methods for our acoustic modeling. Our experiments indicate that, compared with classic LSTM, our architecture shows more than 8% relative reduction in Phone Error Rate (PER) on TIMIT tasks. At the same time, our residual fast LSTM approach shows 4% relative reduction in PER on the same task. Besides, we find that all this architecture could have good results on THCHS-30, Librispeech and Switchboard corpora.

📄 PDF Abstract BibTeX arXiv:1708.05682

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
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition

2020-06-30 · Maarten Van Segbroeck, Harish Mallidih, Brian King, I-Fan Chen 외

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been rep…

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

High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model

2020-03-17 · Jinyu Li, Rui Zhao, Eric Sun, Jeremy H. M. Wong 외

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative t…

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

Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition

2014-02-05 · Haşim Sak, Andrew Senior, Françoise Beaufays

Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNN…

Handwriting RecognitionLanguage ModelingLanguage Modellingspeech-recognition+1

Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer

2018-01-02 · Kanishka Rao, Haşim Sak, Rohit Prabhavalkar

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language mod…

DecoderLanguage ModelingLanguage Modellingspeech-recognition+1

The Microsoft 2017 Conversational Speech Recognition System

2017-08-21 · W. Xiong, L. Wu, F. Alleva, J. Droppo 외

We describe the 2017 version of Microsoft's conversational speech recognition system, in which we update our 2016 system with recent developments in neural-network-based acoustic and language modeling to further advance …

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition