Would a transcript of speech on the screen during interpreting be useful? Thread poster: EnglishAbeille
|
Speech-to-text technologies are getting ahead. I think interpreters could have a device which would record all the speakers say and would show the transcript of their speech on the screen. Looking at the text while you are interpreting would make this job much easier. It might already exist but I have found only few concepts. I've already talked to some people and one of them said that he could create such a mobile application but he is interested to know if it will be... See more Speech-to-text technologies are getting ahead. I think interpreters could have a device which would record all the speakers say and would show the transcript of their speech on the screen. Looking at the text while you are interpreting would make this job much easier. It might already exist but I have found only few concepts. I've already talked to some people and one of them said that he could create such a mobile application but he is interested to know if it will be successful since it’ll take his time and money. I would appreciate if you shared your thoughts. Would this kind of device be useful for you in interpreting? And if yes, do you think it's worth paying any money? ▲ Collapse | | | I doubt I'd ever use it | Jul 3, 2017 |
This may vastly depend on the interpreter him/herself. I personally would be immensely distracted by the text in front of my eyes, so I think my own quality of work would go down with such a thing. Even when I take notes, it's mostly numbers (including dates and stuff) with a bit of proper names on side. But not phrases/words, no. I know that approaches to all this vary from interpreter to interpreter, so maybe someone could find it useful, though. And we are not even taking i... See more This may vastly depend on the interpreter him/herself. I personally would be immensely distracted by the text in front of my eyes, so I think my own quality of work would go down with such a thing. Even when I take notes, it's mostly numbers (including dates and stuff) with a bit of proper names on side. But not phrases/words, no. I know that approaches to all this vary from interpreter to interpreter, so maybe someone could find it useful, though. And we are not even taking into account the level of accuracy of modern speech recognition software. If YouTube suffices for an example, I have seen there several automatically compiled subtitles (with the help of speech recognition, of course, and it's Google we're talking about) which barely hit the spot. In one video in English, where speakers had quite clear pronounciation, subtitles were gibberish. Another video had subtitles in French, because speech recognition software "recognized" the language of the video as French. Alas, the video itself was in German. And those are recent examples, not something from 2007 or whenever. If you interpret during a conference, where the speaker has his/her speech written on a piece of paper, you'd really like to have a copy of it in front of you, no doubt. But instant recognition of living, non-scripted speech... Doubtful. ▲ Collapse | | | No, it wouldn't | Jul 4, 2017 |
It would not be useful in the least, in my opinion. | | |
It is already the case in some meetings (for example at the ITPY hearings). It is very useful especially when it comes to big numbers that you would otherwise miss. | |
|
|
Daryo United Kingdom Local time: 22:04 Serbian to English + ... Of very limited interest | Apr 20, 2018 |
it would be more of a distraction than useful. If you have to divide your attention between the live speaker and the inevitably delayed speech-to-text rendition, you would be put in the same position as having to listen to someone speaking in a echo chamber. Participants in a meeting may well be seen as speaking, but most of the information conveyed is non-verbal, and the displayed text [even if there's never any mistake] says NOTHING about the rhy... See more it would be more of a distraction than useful. If you have to divide your attention between the live speaker and the inevitably delayed speech-to-text rendition, you would be put in the same position as having to listen to someone speaking in a echo chamber. Participants in a meeting may well be seen as speaking, but most of the information conveyed is non-verbal, and the displayed text [even if there's never any mistake] says NOTHING about the rhythm of the sentence, voice intonations etc. IOW you can't ignore the live speaker and just read the displayed text (ergo: it would be like an echo chamber) Not to forget the small technical details that speech-to-text might work reasonably well in English (if it's not some very specialised terminology), but not so well or not at all for other languages, and even for English I doubt that you can trust speech-to-text software never to make some silly mistake and trip you when you have only seconds to deliver a usable output. Sounds to me like like the twin brother of Machine Translation - the day it starts really working, most humans would have anyway already been made redundant by machines. ▲ Collapse | | | To report site rules violations or get help, contact a site moderator: You can also contact site staff by submitting a support request » Would a transcript of speech on the screen during interpreting be useful? Wordfast Pro | Translation Memory Software for Any Platform
Exclusive discount for ProZ.com users!
Save over 13% when purchasing Wordfast Pro through ProZ.com. Wordfast is the world's #1 provider of platform-independent Translation Memory software. Consistently ranked the most user-friendly and highest value
Buy now! » |
| TM-Town | Manage your TMs and Terms ... and boost your translation business
Are you ready for something fresh in the industry? TM-Town is a unique new site for you -- the freelance translator -- to store, manage and share translation memories (TMs) and glossaries...and potentially meet new clients on the basis of your prior work.
More info » |
|
| | | | X Sign in to your ProZ.com account... | | | | | |