--- title: "Carl Case — author profile and papers" description: "Carl Case: 2 papers on Elamur Research (2014–2015), h-index 7 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/carl-case/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/carl-case/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Carl Case # Carl Case Carl Case works on automatic [speech recognition](https://md.research.elamur.ai/free/en/topics/speech/), and both papers here come from 2014 and 2015. The recurring question is whether the long chain of separately engineered parts in a conventional recognizer can be collapsed into a single neural network trained end to end. That chain includes features, acoustic and pronunciation models, and phoneme dictionaries. The method in both papers pairs recurrent networks trained with the CTC loss with very large speech corpora and multi-GPU training built for speed. The most cited of the two is [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://md.research.elamur.ai/free/en/papers/amodei-2015-deep-speech-2-end-end/) (2015). It stacks convolutional and recurrent layers, adds Batch Normalization to the recurrent part, and trains on thousands of hours of English and Mandarin audio supplemented with synthetic augmentation. The paper also describes a synchronous SGD training setup, chosen because it is easier to debug, and reports a 7x speedup over the first system. It also measures human transcription accuracy directly so that comparisons to people rest on a real baseline. The earlier [Deep Speech: Scaling up end-to-end speech recognition](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/) (2014) laid the groundwork. Its deliberately simple network maps spectrograms directly to English characters with no alignment between transcripts and audio, and it was designed to cope better with noisy conditions. Across these two years the work moves from a single-language, English-only model toward a system meant to carry over to a second, very different language, Mandarin. The later paper puts more weight on engineering for scale, such as faster training and a pruned beam search for language-model decoding. Case's papers here are co-written with a stable group that includes [Adam Coates](https://md.research.elamur.ai/free/en/authors/adam-coates/), [Bryan Catanzaro](https://md.research.elamur.ai/free/en/authors/bryan-catanzaro/), [Erich Elsen](https://md.research.elamur.ai/free/en/authors/erich-elsen/), [Greg Diamos](https://md.research.elamur.ai/free/en/authors/greg-diamos/) and [Jared Casper](https://md.research.elamur.ai/free/en/authors/jared-casper/). [Andrew Y. Ng](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/) and [Dario Amodei](https://md.research.elamur.ai/free/en/authors/dario-amodei/) also appear among the co-authors. 2 papers on this site · 2014–2015 Carl Case has 2 papers on this site, in 2014–2015, most of them on [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/); often with [Adam Coates](https://md.research.elamur.ai/free/en/authors/adam-coates/), [Bryan Catanzaro](https://md.research.elamur.ai/free/en/authors/bryan-catanzaro/), [Erich Elsen](https://md.research.elamur.ai/free/en/authors/erich-elsen/). [OpenAlex](https://openalex.org/A5010691025) · [**h-index 7**](https://openalex.org/authors/A5010691025) · [12 works](https://openalex.org/works?filter=author.id:A5010691025) · [2 645 citations](https://openalex.org/works?filter=author.id:A5010691025&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/carl-case/#papers) · [331 citations in our library](https://md.research.elamur.ai/free/en/authors/carl-case/cited-by/) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Carl+Case) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Carl+Case) · [dblp](https://dblp.org/search?q=Carl+Case) · [ACL Anthology](https://aclanthology.org/search/?q=Carl+Case) ## Affiliations - [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) · Stanford, United States —2011 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Speech & spoken language 2](https://md.research.elamur.ai/free/en/topics/speech/) ## Works by year ### 2010s [**2015** 1 paper](https://md.research.elamur.ai/free/en/papers/amodei-2015-deep-speech-2-end-end/) · [**2014** 1 paper](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/) ## Papers The most cited first (OpenAlex and our library). 1. **[Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://md.research.elamur.ai/free/en/papers/amodei-2015-deep-speech-2-end-end/)** *(2015 · 2 302 citations)* Conventional speech recognizers are assembled from many hand-tuned parts, including feature extractors, acoustic, pronunciation and language models, and speaker adaptation. 2. **[Deep Speech: Scaling up end-to-end speech recognition](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/)** *(2014 · 1 575 citations)* Conventional speech recognizers chain together many hand-tuned components, including engineered features, acoustic models, HMMs and phoneme dictionaries. ## Co-authors here 10 co-authors with a page, the most papers together first. - [Adam Coates](https://md.research.elamur.ai/free/en/authors/adam-coates/) ×2 - [Bryan Catanzaro](https://md.research.elamur.ai/free/en/authors/bryan-catanzaro/) ×2 - [Erich Elsen](https://md.research.elamur.ai/free/en/authors/erich-elsen/) ×2 - [Greg Diamos](https://md.research.elamur.ai/free/en/authors/greg-diamos/) ×2 - [Jared Casper](https://md.research.elamur.ai/free/en/authors/jared-casper/) ×2 - [Andrew Y. Ng](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/) - [Dario Amodei](https://md.research.elamur.ai/free/en/authors/dario-amodei/) - [Jingdong Chen](https://md.research.elamur.ai/free/en/authors/jingdong-chen/) - [Ryan Prenger](https://md.research.elamur.ai/free/en/authors/ryan-prenger/) - [Sanjeev Satheesh](https://md.research.elamur.ai/free/en/authors/sanjeev-satheesh/) ## Cited by Papers of our library cite their works 331 times (of the 140 884 papers whose bibliographies we read); [23 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/carl-case/cited-by/).