Deep segmental neural networks for speech recognition

By Ossama Abdel-Hamid, Li Deng, Dong Yu, Hui Jiang. 2013

46 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

A segmental framework for fully-unsupervised large-vocabulary speech recognition (2016, methodology): “A simple and fast approach to obtain acoustic word embeddings is to uniformly downsample so that any segment is represented by the same ﬁxed number of vectors [25,47].”
Time-series modeling with undecimated fully convolutional neural networks (2015, methodology): “For example, in [6,7] a CNN was used to predict the phoneme class conditional probability for a segment of raw input signal.”
Conditional-Computation-Based Recurrent Neural Networks for Computationally Efficient Acoustic Modelling (2018, methodology): “In the past, the limitations imposed by the fixed-rate segmentation scheme inspired the so called segment-based ASR methods [9, 10, 11] that, in contrast to our approach, do not focus primarily on computational efficiency as they typically require many more decoding operations than frame-based syste”
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, background): “The section XI discusses on 0 10 20 30 40 First-pass SCRF [13] Boundary-factored SCRF[14] Deep Segmental NN[15] Discriminative segmetal.”
Segmental Recurrent Neural Networks for End-to-End Speech Recognition (2016, methodology): “In particular, feed-forward neural networks have been used with segmental CRFs for speech recognition [19, 20].”
Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings (2013, background): “These include downsampling [13, 14, 15, 16], phonetic acoustic model-derived features [17, 18], and convolutional deep neural networks [19].”
Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments (2018, background): “Recent approaches represent segments with RNNs [15], or Deep Neural Networks (DNN) together with subsampling, pooling and duration information [16, 17].”