Automatic Speech Recognition: A Deep Learning Approach

By Dong Yu, Li Deng. 2014

689 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Speech & Audio, 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 Speech & Audio

In Signal Processing

Citations in the corpus

Light Gated Recurrent Units for Speech Recognition (2018, methodology): “p://ieeexplore.ieee.org/ document/8323308/ systems and natural language processing, just to name a few. Another ﬁeld that has been transformed by this technology is Automatic Speech Recognition (ASR) [12]. Thanks to modern Deep Neural Networks (DNNs), current speech recognizers are now able to signi”
Language Modeling with Gated Convolutional Networks (2016, background): “Language models are a critical part of systems for speech recognition (Yu & Deng, 2014) and machine translation (Koehn, 2010).”
An Analysis of Neural Language Modeling at Multiple Scales (2018, methodology): “Trained LMs are useful in many applications including speech recognition (Yu & Deng, 2014), machine translation (Koehn, 2009), natural language generation (Radford et al., 2017; Merity et al., 2017a), learning token embeddings, and as a general-purpose feature extractor for downstream tasks (P.…”
The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments (2015, background): “During the last decade, much research has been devoted to improve Automatic Speech Recognition (ASR) performance [1].”
VoiceHome-2, an extended corpus for multichannel speech processing in real homes (2019, neutral): “This precludes the use of machine learning techniques ( e.g. , based on deep neural networks) for speech enhancement and ASR (Weninger et al., 2015; Yu and Deng, 2014), which require data collected in distinct homes for training, validation, and testing.”
A network of deep neural networks for Distant Speech Recognition (2017, result): “ion with a machine is required. A crucial role in improving current solutions is being played by deep learning [1], which has recently contributed to outperforming previous HMM-GMM speech recognizers [2]. The progress in the ﬁeld was also fostered by the considerable success of some international ch”
Environmental sound classification with convolutional neural networks (2015, background): “A thorough coverage of current deep learning methods and their applications in various contexts, including speech and audio processing, can be found in recently published books discussing this topic [21–23].”
Modeling speaker variability using long short-term memory networks for speech recognition (2015, background): “Yet another group of speaker adaptation approaches are the speaker-aware training[11], in which the speaker information is provided to the network in hope that the DNN training algorithm can automatically ﬁgure out the speaker normalization.”
Decision Forests, Convolutional Networks and the Models in-Between (2016, neutral): “Two learning approaches have gained particular attention: (i) random forests [1, 4, 5, 22], as used e.g . in Microsoft Kinect [15]; and (ii) deep neural networks (DNNs) [13, 20], as used for speech recognition [31] and image classiﬁ-cation [9], among other applications.”
Conditional-Computation-Based Recurrent Neural Networks for Computationally Efficient Acoustic Modelling (2018, background): “In recent years deep bidirectional RNN’s have set the state-ofthe-art performance in several ASR tasks [1, 2, 3, 4, 5, 6].”
A French Corpus for Distant-Microphone Speech Processing in Real Homes (2016, positive): “, based on deep neural networks) for speech enhancement and recognition [28, 29], which require data collected in distinct homes for training, validation, and testing.”
The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices (2015, methodology): “Our acoustic models were built following a standard recipe [15].”
Distributed Compressive Sensing: A Deep Learning Approach (2015, background): “Similar to all deep learning methods, it has the important feature of learning the structure of S from the raw data automatically.”
The Pytorch-kaldi Speech Recognition Toolkit (2018, background): “Over the last years, we witnessed a progressive improvement and maturation of Automatic Speech Recognition (ASR) technologies [1, 2], that have reached unprecedented performance levels and are nowadays used by millions of users worldwide.”
Scalable training of deep learning machines by incremental block training with intra-block parallel optimization and blockwise model-update filtering (2016, methodology): “Index Terms— Incremental block training, parallel optimization, blockwise model-update filtering, deep learning, LVCSR”
A Review on Automatic Speech Recognition Architecture and Approaches (2016, background): “The generative component is mostly exploited to help with discrimination as the final goal of the hybrid architecture [16][17][18].”