Path: csiph.com!v102.xanadu-bbs.net!xanadu-bbs.net!feeder.erje.net!eu.feeder.erje.net!eternal-september.org!feeder.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: =?UTF-8?B?Sm9zaHVhIENyYW5tZXIg8J+Qpw==?= Newsgroups: comp.lang.java.programmer Subject: Re: Artificial Intelligence with Java Date: Sun, 22 Jun 2014 21:20:12 -0500 Organization: A noiseless patient Spider Lines: 13 Message-ID: References: <21b372c0-200e-4587-9fa1-953c8a3d080d@googlegroups.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Injection-Date: Mon, 23 Jun 2014 02:20:12 +0000 (UTC) Injection-Info: mx05.eternal-september.org; posting-host="3ef5a0442a8ddc1c581244a76b4a7004"; logging-data="12937"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18cs8bvPbEVm4DKSUmGUg7I9NV33nYx5wg=" User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Thunderbird/31.0 In-Reply-To: Cancel-Lock: sha1:ga671nE827GPCqYe4JSRbTRbTTI= Xref: csiph.com comp.lang.java.programmer:28819 On 6/21/2014 12:23 AM, Roedy Green wrote: > I suspect you will do much better analysing the raw voice rather than > a transcript. All the time on the net people mistake jokes, irony etc > because of the lack of timbre cues. I doubt it. Transcripts have the advantage that the individual semantic units are unambiguous, whereas aural processing needs to identify and translate phonemes from a fairly noisy signal and has to cover a much broader set of regional varieties in aural media than in written media. -- Beware of bugs in the above code; I have only proved it correct, not tried it. -- Donald E. Knuth