--- title: "Exploration of Speech enabled System for English — Sharma 2013" description: "It offers no new algorithm, dataset or experiment. 6 references. This 2013 conference paper surveys speech-enabled computing for English." authors: ["Kamlesh Sharma", "T. Suryakanthi", "T. V. Prasad"] year: 2013 venue: "arXiv:1304.8013" source: "https://arxiv.org/abs/1304.8013" doi: "10.48550/arxiv.1304.8013" arxiv: "1304.8013" licence: "arXiv — non-exclusive license to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/sharma-2013-exploration-speech-enabled-system-english/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sharma-2013-exploration-speech-enabled-system-english/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2013](https://md.research.elamur.ai/free/en/papers/2013/page/2/) / Exploration of Speech enabled System for English # Exploration of Speech enabled System for English **Authors:** [Kamlesh Sharma](https://md.research.elamur.ai/free/en/authors/kamlesh-sharma/), T. Suryakanthi and T. V. Prasad · **Year:** 2013 · **Venue:** arXiv:1304.8013 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1304.8013) · [PDF](https://arxiv.org/pdf/1304.8013) · [DOI 10.48550/arxiv.1304.8013](https://doi.org/10.48550/arxiv.1304.8013) · [arXiv 1304.8013](https://arxiv.org/abs/1304.8013) · [OpenAlex](https://openalex.org/W6941507995) **Citations:** 7 citations (OpenAlex, 2026-10-14) ## Summary This 2013 conference paper surveys speech-enabled computing for English. It offers no new algorithm, dataset or experiment. The authors describe what speech recognition (speech-to-text, STT) does and separate speaker-trained "voice recognition" from speaker-independent recognition. They then review speech features built into operating systems (Mac OS X Lion, Windows XP, Vista and 7) and catalogue commercial and research products in comparison tables: 29 recognition systems and 5 developer tools. The paper covers typical application areas, including dictation, command and control, telephony and call routing, web search, education, medicine and accessibility. It also groups common software features, such as commanding, dictating, calculating, mail and fax, and correcting misrecognitions. The authors list claimed benefits, like faster input and less strain for users with RSI, and give practical advice on voice user interface (VUI) design. The paper is mainly useful as a snapshot of the speech-technology landscape around 2012–2013 and as a source of design guidance for spoken interaction. It provides no measured accuracy results. ## Key points - The paper is descriptive and has no evaluation of its own. Tables compare OS speech features and list 29 English speech systems and 5 speech tools. - The tools covered are AT&T Watson API, CSLU Toolkit, HTK (Hidden Markov Model Toolkit), iSpeech ASR API and Nuance Recognizer. The paper says Nuance Recognizer is used in over 79 languages. - Windows Vista and Windows 7 ship version 8.0 of Microsoft's recognition engine. It supports English, French, Spanish, German, Japanese and both Simplified and Traditional Chinese. - The survey claims users can dictate at least about 3 times faster than they type. The best-suited users are people with disabilities, people whose hands and eyes are busy, people without a keyboard or screen, and people with few computer skills. - Other systems mentioned include Loquendo ASR (neural-network based, speaker independent), Vocapia VoxSigma, Google Voice Search and the IIT Kanpur startup Simmortel. ## Interesting ideas - Design the interface for its audience: newcomers need guidance and help prompts, while expert users want few prompts and the option to give several pieces of information in one utterance, in any order ("mixed initiative"). - Automation fits short, routine transactions well and tends to fail on complex open inquiries, so some tasks are better handed to a human than forced through the system. - Recognition errors are fixed by letting the user pick from alternative hypotheses for a word or phrase, or by spelling the word out. - A system is easier to use the more closely it follows the user's mental model of the task. - Splitting speaker-adapted from speaker-independent recognition shows that per-user adaptation trades setup effort for accuracy. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (frames): Frame filling should accept role fillers in whatever order and combination the text provides, without assuming a fixed slot sequence. - **I2** (answer): Readers could estimate how complex a question is and abstain or flag it explicitly, rather than produce a confident wrong answer. - **I3** (tree): The parser could keep a small n-best set of alternative tags or attachments, so a later stage can choose another reading when meaning breaks down. - **I4** (back): Generated explanations could follow how a person describes the situation, such as who did what in order, rather than the internal graph layout. - **I5** (learn): The same split could separate general models from domain- or genre-adapted ones, evaluating each on held-out text from other domains as a control. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works 🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 1,373 works · [🎙️ Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) · 233 works ## Cite Cite as: Kamlesh Sharma, T. Suryakanthi and T. V. Prasad. 2013. Exploration of Speech enabled System for English. arXiv:1304.8013. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{sharma2013exploration, title = {{Exploration of Speech enabled System for English}}, author = {Kamlesh Sharma, T. Suryakanthi and T. V. Prasad}, year = {2013}, doi = {10.48550/arxiv.1304.8013}, eprint = {1304.8013}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1304.8013} } ``` - [← previous An analysis of disagreement-provoking factors in the analysis of epistemic modality and evidentiality: the case of English adverbials](https://md.research.elamur.ai/free/en/papers/carretero-2013-analysis-disagreement-provoking-factors-analysis/) - [next → Semantic Annotation of Textual Entailment](https://md.research.elamur.ai/free/en/papers/toledo-2013-semantic-annotation-textual-entailment/) - [↑ back to papers of 2013](https://md.research.elamur.ai/free/en/papers/2013/page/2/) ## References 6 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Jennifer Ouellette, Speech Recognition: Humanizing the Interface, Industrial Physicist, Vol. 4 Issue 1, pp. 20, 1998 [find](https://scholar.google.com/scholar?q=Jennifer+Ouellette%2C+Speech+Recognition%3A+Humanizing+the+Interface%2C+Industrial+Physicist%2C+Vol%2E+4+Issue+1%2C+pp%2E+20%2C+1998) 2. Markus Forsberg, Why is Speech Recognition Difficult?, Chalmers University of Technology, Feb2003. [find](https://scholar.google.com/scholar?q=Markus+Forsberg%2C+Why+is+Speech+Recognition+Difficult%3F%2C+Chalmers+University+of+Technology%2C+Feb2003%2E) 3. Swetanka Kumar Mishra & Kirti Chawla. “RTOS Design & Implementation”, Media Platform Group, Samsung Electronics Limited, India, 2004 [find](https://scholar.google.com/scholar?q=Swetanka+Kumar+Mishra+%26+Kirti+Chawla%2E+%E2%80%9CRTOS+Design+%26+Implementation%E2%80%9D%2C+Media+Platform+Group%2C+Samsung+Electronics+Limited%2C+India%2C+2004) 4. Diana Huggins, Configure Text-to-Speech in Microsoft Windows XP, In Tech Republic Version 1.0, Jan. 2006. [find](https://scholar.google.com/scholar?q=Diana+Huggins%2C+Configure+Text%2Dto%2DSpeech+in+Microsoft+Windows+XP%2C+In+Tech+Republic+Version+1%2E0%2C+Jan%2E+2006%2E) 5. Esther Levin and Amir M. Manš., Voice User Interface Design for Automated Directory Assistance, Fourth International Conference on Spoken Language, 1996. [find](https://scholar.google.com/scholar?q=Esther+Levin+and+Amir+M%2E+Man%C5%A1%2E%2C+Voice+User+Interface+Design+for+Automated+Directory+Assistance%2C+Fourth+International+Conference+on+Spoken+Language%2C+1996%2E) 6. Daniel Mecanovic and Hao Shi, Voice User Interface Design for a Telephone Application Using VoiceXML, APWeb'05 Proceedings of the 7th Asia-Pacific web conference on Web Technologies Research and Development , Pages 1058-1061, 2005 [find](https://scholar.google.com/scholar?q=Daniel+Mecanovic+and+Hao+Shi%2C+Voice+User+Interface+Design+for+a+Telephone+Application+Using+VoiceXML%2C+APWeb%2705+Proceedings+of+the+7th+Asia%2DPacific+web+conference+on+Web+Technologies+Research+and+Devel) *Updated 24 October 2026*