Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP Posting-Version: version B 2.10.1 6/24/83; site fortune.UUCP Path: utzoo!watmath!clyde!burl!ulysses!mhuxl!ihnp4!fortune!polard From: polard@fortune.UUCP (Henry Polard) Newsgroups: net.ai Subject: Re: Understanding speech versus hearing words Message-ID: <4138@fortune.UUCP> Date: Wed, 5-Sep-84 13:00:24 EDT Article-I.D.: fortune.4138 Posted: Wed Sep 5 13:00:24 1984 Date-Received: Thu, 6-Sep-84 04:47:20 EDT References: <13053@sri-arpa.UUCP> Organization: Fortune Systems, Redwood City, CA Lines: 30 Which hip was burned? Which ship was burned? Which chip was burned? and Which Chip was spurned? all sound the same when spoken at the speed of conversational speech. This is evidence that in order to recognize words in continuous speech you (and presumably a speech-recognition apparatus) need to understand what the speaker is talking about. There seem to be two reasons why understanding is necessary for word recognition in continuous speech: 1. The existence of homonyms. This is why "It's a good read." sounds the same as: "It's a good reed," and why the two sentences could not be distinguished without a knowledge of the context. 2. Sandhi, or sound changes at word boundaries. The sounds at the end of a word tend to blend into the sounds at the beginning of the next word in conversation, making words sound as if they ran into each other and making words sound differently than they would when said in isolation. The resulting ambiguities are ususally resolved by context. Speech rarely occurs without some sort of context, and even then the first thing that usually happens is to establish a context for what is to follow. To paraphrase Edsgar Dijkstra: "Asking whether computers will understand speech is like asking whether submarines swim." -- Henry Polard (You bring the flames - I'll bring the marshmallows.) {ihnp4,cbosgd,amd}!fortune!polard