Challenges in adopting speech recognition

By Li Deng, Xuedong Huang. 2004

190 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

1. Li Deng
2. Jianfeng Gao
3. Dong Yu
4. Bhaskar Mitra
5. Nick Craswell
6. Xiaodong He
7. Yoshua Bengio
8. Kyunghyun Cho

In Speech & Audio

1. Li Deng
2. Dong Yu
3. Usa
4. W. Redmond
5. Jianfeng Gao
6. Li Deng
7. A. Acero
8. Maja Pantic

In Signal Processing

1. Li Deng
2. Dong Yu
3. A. Acero
4. Jianfeng Gao
5. Jinyu Li
6. Usa
7. W. Redmond
8. Li Deng

Citations in the corpus

• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016, background): “Another example is the very large speech databases collected over 20 years by DARPA that enabled successes of deep learning in speech recognition [11].”
• Deep Learning: Methods and Applications (2014, background): “Subsequent work added a new hidden layer into the dynamic model to explicitly account for the target-directed, articulatory-like properties in human speech generation [45, 73, 74, 83, 96, 75, 90, 231, 232, 233, 251, 282].”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Subsequent work added a new hidden layer into the dynamic model so as to explicitly account for the target-directed, articulatory-like properties in human speech generation (Deng and Ramsay, 1997; Bridle et al., 1998; Deng, 1999; Picone et al., 1999; Deng, 2003; Minami et al., 2002; Deng and Huang, ”
• Multi-sensory speech processing: incorporating automatically extracted hidden dynamic information (2005, background): “The presence of noise not only renders speech unintelligible but also results in poor performance of automatic speech recognition engines [8].”
• Design and Learning of Output Representations for Speech Recognition (2013, background): “Likewise, it has also 101 been well understood for a long time that the use of phonetic or its finer state sequences, even with 102 contextual dependency, in engineering speech recognition systems is inadequate in representing 103 such rich structure [5][12][14][27] and thus leaving a promising open”
• Human computing and machine understanding of human behavior: a survey (2006, background): “The how context question is usually addressed as a problem of human sensing (see the state of the art in human sensing in the text above; for a survey on speech recognition see [13]).”
• Dynamic Speech Models: Theory, Algorithms, and Applications (2006, methodology): “, [10–13]).”
• Structured speech modeling (2006, background): “…in the field understand the fragile nature of the current speech recognition system design, and have advocated that new, serious research is needed to overcome some fundamental limitations of the current speech recognition technology (e.g., [3], [6], [9], [29], [34], [40], [42], [49], [53], [59]).”
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016, background): “Similarly, the large speech database collected over 20 years by DARPA enabled new breakthroughs in speech recognition performance from deep learning models Deng and Huang [2004].”