Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models
نویسندگان
چکیده
Online-Recognition requires the acoustic model to provide posterior probabilities after a limited time delay given the online input audio data. This necessitates unidirectional modeling and the standard solution is to use unidirectional long short-term memory (LSTM) recurrent neural networks (RNN) or feedforward neural networks (FFNN). It is known that bidirectional LSTMs are more powerful and perform better than unidirectional LSTMs. To demonstrate the performance difference, we start by comparing several different bidirectional and unidirectional LSTM topologies. Furthermore, we apply a modification to bidirectional RNNs to enable online-recognition by moving a window over the input stream and perform one forwarding through the RNN on each window. Then, we combine the posteriors of each forwarding and we renormalize them. We show in experiments that the performance of this online-enabled bidirectional LSTM performs as good as the offline bidirectional LSTM and much better than the unidirectional LSTM.
منابع مشابه
Forward-Backward Convolutional LSTM for Acoustic Modeling
An automatic speech recognition (ASR) performance has greatly improved with the introduction of convolutional neural network (CNN) or long-short term memory (LSTM) for acoustic modeling. Recently, a convolutional LSTM (CLSTM) has been proposed to directly use convolution operation within the LSTM blocks and combine the advantages of both CNN and LSTM structures into a single architecture. Thi...
متن کاملDynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition
Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in ...
متن کاملCombining pattern recognition and deep-learning-based algorithms to automatically detect commercial quadcopters using audio signals (Research Article)
Commercial quadcopters with many private, commercial, and public sector applications are a rapidly advancing technology. Currently, there is no guarantee to facilitate the safe operation of these devices in the community. Three different automatic commercial quadcopters identification methods are presented in this paper. Among these three techniques, two are based on deep neural networks in whi...
متن کاملFast and accurate recurrent neural network acoustic models for speech recognition
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic models using such LSTM RNNs can be equaled by sequence trained phone models in...
متن کاملModeling speaker variability using long short-term memory networks for speech recognition
Speaker adaptation of deep neural networks (DNNs) based acoustic models is still a challenging area of research. Considering that long short-term memory (LSTM) recurrent neural networks (RNNs) have been successfully applied to many sequence prediction and sequence labeling tasks, we propose to use LSTM RNNs for modeling speaker variability in automatic speech recognition (ASR). Firstly, the LST...
متن کامل