Journal article · 2016 · Open access

Deep learning: from speech recognition to language and multimodal processing

Li Deng

APSIPA Transactions on Signal and Information Processing, 5(1) · Published 1 January 2016 · DOI 10.1017/atsip.2015.22

Open PDFView at the publisherCite this paper

In brief

“Deep learning: from speech recognition to language and multimodal processing” is a 2016 journal article by Li Deng, published in APSIPA Transactions on Signal and Information Processing. OpenAlex counts 113 citations as of 22 November 2026, which puts it in the top 8% of works published in 2016 by citations. It is open access under a CC BY licence: the full text is free to read at APSIPA Transactions on Signal and Information Processing.

Citations
113
Most cited in
2025 (20)
Field-weighted impact
3.88
References
175
Authors
1

Abstract

Deep learning: from speech recognition to language and multimodal processing li dengWhile artificial neural networks have been in existence for over half a century, it was not until year 2010 that they had made a significant impact on speech recognition with a deep form of such networks.This invited paper, based on my keynote talk given at Interspeech conference in Singapore in September 2014, will first reflect on the historical path to this transformative success, after providing brief reviews of earlier studies on (shallow) neural networks and on (deep) generative models relevant to the introduction of deep neural networks (DNN) to speech recognition several years ago.The role of well-timed academicindustrial collaboration is highlighted, so are the advances of big data, big compute, and the seamless integration between the application-domain knowledge of speech and general principles of deep learning.Then, an overview is given on sweeping achievements of deep learning in speech recognition since its initial success.Such achievements, summarized into six major areas in this article, have resulted in across-the-board, industry-wide deployment of deep learning in speech recognition systems.Next, more challenging applications of deep learning, natural language and multimodal processing, are selectively reviewed and analyzed.Examples include machine translation, knowledgebase completion, information retrieval, and automatic image captioning, where fresh ideas from deep learning, continuous-space embedding in particular, are shown to be revolutionizing these application areas albeit with less rapid pace than for speech and image recognition.Finally, a number of key issues in deep learning are discussed, and future directions are analyzed for perceptual tasks such as speech, image, and video, as well as for cognitive tasks involving natural language.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Deng, L. (2016). Deep learning: from speech recognition to language and multimodal processing. APSIPA Transactions on Signal and Information Processing, 5(1). https://doi.org/10.1017/atsip.2015.22

MLA 9

Deng, Li. “Deep learning: from speech recognition to language and multimodal processing.” APSIPA Transactions on Signal and Information Processing, vol. 5, no. 1, 2016. https://doi.org/10.1017/atsip.2015.22.

Chicago

Deng, Li. 2016. “Deep learning: from speech recognition to language and multimodal processing.” APSIPA Transactions on Signal and Information Processing 5 (1). https://doi.org/10.1017/atsip.2015.22.

Harvard

Deng, L. (2016) ‘Deep learning: from speech recognition to language and multimodal processing’, APSIPA Transactions on Signal and Information Processing, 5(1). doi:10.1017/atsip.2015.22.

IEEE

L. Deng, “Deep learning: from speech recognition to language and multimodal processing,” APSIPA Transactions on Signal and Information Processing, vol. 5, no. 1, 2016, doi: 10.1017/atsip.2015.22.

BibTeX

@article{deng2016deep,
  title     = {{Deep learning: from speech recognition to language and multimodal processing}},
  author    = {Deng, Li},
  journal   = {APSIPA Transactions on Signal and Information Processing},
  year      = {2016},
  volume    = {5},
  number    = {1},
  doi       = {10.1017/atsip.2015.22},
  url       = {https://doi.org/10.1017/atsip.2015.22}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201733
20181111
201977
20201010
20211010
20221010
20231414
20241818
20252020
202688

Its field-weighted citation impact is 3.88: it has been cited 3.88 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis

  • deep neural network
  • speech recognition
  • natural language processing
  • multimodal processing
  • machine translation
  • knowledge base completion
  • information retrieval
  • image captioning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Deng, L. (2016). Deep learning: from speech recognition to language and multimodal processing. APSIPA Transactions on Signal and Information Processing, 5(1). https://doi.org/10.1017/atsip.2015.22

How many times has this paper been cited?

113 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at APSIPA Transactions on Signal and Information Processing: sign in and open the PDF from this page.

Who wrote this paper?

Li Deng.

What is the DOI of this paper?

10.1017/atsip.2015.22, permanently at https://doi.org/10.1017/atsip.2015.22. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.