Conversational Speech Transcription Using Context-Dependent Deep Neural Networks

By Frank Torsten Bernd Seide, Gang Li, Dong Yu. 2012

930 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio

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 Speech & Audio

Citations in the corpus

Deep Generative Stochastic Networks Trainable by Backprop (2013, background): “However, the most impressive recent results have been obtained with purely supervised learning techniques for deep networks, in particular for speech recognition (Dahl et al., 2010; Deng et al., 2010; Seide et al., 2011) and object recognition (Krizhevsky et al., 2012).”
GSNs : Generative Stochastic Networks (2015, background): “recognition (Dahl et al., 2010; Deng et al., 2010; Seide et al., 2011) and object recognition (Krizhevsky et al.”
Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin (2015, methodology): “More recently DNNs have become a fixture in the ASR pipeline with almost all state of the art speech work containing some form of deep neural network (Mohamed et al., 2011; Hinton et al., 2012; Dahl et al., 2011; N. Jaitly & Vanhoucke, 2012; Seide et al., 2011).”
Representation Learning: A Review and New Perspectives (2012, background): “For that reason, much of the actual effort in deploying machine learning algorithms goes into the design of preprocessing pipelines and data transformations that result in a representation of the data that can support effective machine learning.”
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks (2016, background): “In several areas ( e.g., vision and speech), however, shallow networks cannot compete with deep models [14].”
Do Deep Nets Really Need to be Deep? (2013, background): “On the TIMIT phoneme recognition and CIFAR-10 image recognition tasks, shallow nets can be trained that perform similarly to complex, well-engineered, deeper convolutional architectures.”
Towards Better Analysis of Deep Convolutional Neural Networks (2016, methodology): “ring. 1 INTRODUCTION Deep convolutional neural networks (CNNs) have demonstrated signiﬁcant improvements over traditional approaches in many pattern recognition tasks [31], such as speech recognition [42, 43], image classiﬁcation [17, 30], and video classiﬁcation [27, 58]. More recently, deep CNNs h”
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks (2015, background): “For examples, [2, 37, 39, 40] show significant improvements on the worderror rate of speech-to-text transcription task, which was contributed by the effective and”
Deep Learning: Methods and Applications (2014, methodology): “Over recent years, since the success of the (fully-connected) DNN– HMM hybrid system was demonstrated in [67, 68, 109, 161, 257, 258, 308, 309, 324, 429], many new architectures and nonlinear units have been proposed and evaluated for speech recognition.”
Achieving Human Parity in Conversational Speech Recognition (2016, background): “Expanded coverage of the Microsoft Cognitive Toolkit (CNTK) used to build our models 6.”
Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning (2017, background): “, 2012) and voice recognition (Seide et al., 2011), (2) backpropagation for deep neural networks combined with traditional reinforcement learning algorithms, such as Q-learning (Watkins & Dayan, 1992; Mnih et al.”
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters (2015, background): “7 120TF MSFT-Speech [38] speech recognition 74MB 151MB 0.”
Transformer-Based Acoustic Modeling for Hybrid Speech Recognition (2019, neutral): “Since the introduction of deep learning in automatic speech recognition (ASR) [1], a variety of neural network architectures for acoustic modeling have been explored [2–6].”
Highway long short-term memory RNNS for distant speech recognition (2015, background): “Recently the deep neural network (DNN)-based acoustic models (AMs) greatly improved automatic speech recognition (ASR) accuracy on many tasks [1, 2, 3, 4].”
Big Neural Networks Waste Capacity (2013, background): “te on the 1000-class ImageNet object recognition benchmark 2Mikolov et al. (2011) reduced perplexity on WSJ by 40% and speech recognition absolute word error rate by > 1%. 3For speech recognition, Seide et al. (2011) report relative word error rates decreasing by about 30% on datasets of 309 hour”
Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks (2013, methodology): “The detailed training procedure and decoding technique for CD-DNN-HMMs can be found in [6–8].”