An open community 
of Macintosh users,
for Macintosh users.

FineTunedMac Dashboard widget now available! Download Here

Topic Options
#22946 - 08/07/12 11:22 AM Current status of speech to text?
JoBoy Offline


Registered: 08/05/09
Several years ago, I bought an early version of Dragon Naturally Speaking for a Windows machine. There was nothing I could find for my beloved Mac. I finally threw Dragon Naturally Speaking away. I thought it was a work in progress, but not a real contributor to my work product. Now, I use VMware and Windows 7 on my Mac for Windows apps, but 95% of my work is done on the Mac OS.

One of the things I do is record an extemporaneous speech not to exceed 30 minutes using a pair of Sony digital recorders with microphones clipped to my tie. The pair provide redundancy in case one recorder should fail. The digital recordings are crystal clear. Later, one of the recordings is manually transcribed to a text file. From time to time, I wonder if today's Nuance products for either PC or Mac could convert the speech to text in an easy to use, accurate way. The speeches do not contain any directions for punctuation or formatting, but that is not a problem. That can be handled after the text is available on a word processing document. Given my prior experience and the enormous waste of time it was, I'm leery of trying it again with a "new, improved version." I see that Nuance offers version 12 of Dragon Naturally Speaking for the PC and MacSpeech Scribe for the Mac. It appears that one of these products might get the job done.

Is anyone familiar with the current performance status of these items? Have they truly become useful, productive, and easy to use? The Sony recorders are not mandatory in my case. Mine are several years old and they are strictly for the PC with Sony software, but I see that the iPhone App Store offers Dragon Recorder as a way to feed a recording to either Dragon Naturally Speaking on the PC or MacSpeech Scribe on the Mac. I would hope for a remote mic that I could clip to my tie since holding an iPhone up to my mouth during the talk would be absurd.


Edited by JoBoy (08/07/12 12:29 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#22947 - 08/07/12 12:40 PM Re: Current status of speech to text? [Re: JoBoy]
joemikeb Offline
Moderator

Registered: 08/04/09
Loc: Fort Worth, Texas
I don't have any personal experience with voice recognition — other than Siri on the iPhone/iPad — but my son, a radiologist, uses speech recognition to dictate patient notes. Obviously recognition accuracy is of paramount importance in this setting. The notes use a limited albeit somewhat arcane vocabulary and generally are on the order of half a page in length. The system he uses is customized for the medical profession with particular attention paid to the specialized medical vocabulary. He dictates in a quiet room where the only background noises is the hum of the fan on a PC and he uses purpose built microphone. He always proof reads the dictation results and manually makes any necessary corrections. It is the rare note that does not require at least some correction. Sometimes he only has to manually correct a word or two, sometimes it is more expedient to hit the delete key and start over, and sometimes he resorts to the keyboard. By-the-way this system is not hosted on his PC. Instead the voice is digitized and sent to a dedicated host computer system.

The key factors in accuracy appear to be:
  • No background noise
  • very high quality microphone
  • moderate to slow speech rate
  • somewhat monotonic delivery
_________________________
joemikeb • moderator

Top
#22948 - 08/07/12 12:42 PM Re: Current status of speech to text? [Re: JoBoy]
Virtual1 Offline


Registered: 08/04/09
Loc: Iowa
I've seen them in use at schools recently for speech therapy I think. The school got a grant for 5 or 6 macbooks plus software that came with headphones with mics etc.

It's been my experience with voice recognition that it's more of a novelty and interesting idea than a productive thing. BUT there are rare cases I see from time to time where it's being put to extremely good use. Professionals are using cassette and other handheld recorders and then pass them off to their secretaries/assistants to transcribe into text files. Those assistants use this software to transcribe in and then clean it up by hand. That's usually how you have to go with it, it's never perfect and can leave some very silly and obvious mistakes in the text files if you don't look them over carefully when it's done.

I played with the speech control on the mac a few times, but again it was more of a "that's neat" but too awkward to use. I bet if I was a paraplegic it'd be awesome though. Not useful for the normal non-disabled person though.

As for dragon specifically, they've been on mac for years haven't they? You sound like you looked for it but didn't find it.
_________________________
I work for the Department of Redundancy Department

Top
#22962 - 08/07/12 06:39 PM Re: Current status of speech to text? [Re: Virtual1]
JoBoy Offline


Registered: 08/05/09
Originally Posted By: Virtual1
As for dragon specifically, they've been on mac for years haven't they? You sound like you looked for it but didn't find it.

It's true that Nuance has been doing Mac for years, but I've been doing Apple longer than that. As a young buck, my first personal machine was a brand new Apple II followed by a Lisa and then the first Mac and a long series of Macs until the Mac Pro. I stayed with Mac instead of going for the IBM PC-AT because Apple's Mac and Laser Printer had proportional type with the WYSIWYG correlation between the Mac's screen and the printed documents. IBM did not have it at that time. At my office we used the IBM 32 and then a 34 with a very expensive laser printer but the word processing software could not do WYSIWYG prints so we wasted a pile of paper getting documents finished correctly and IBM charged us for every print we made whether or not it was acceptable.

Nuance began as a PC shop, but acquired Mac stuff to expand their portfolio when Apple began to grow. At one time, my work required me to use some PC apps, so I bought a PC and Dragon was one of the apps I tried. It was before Nuance had Mac stuff and the Mac stuff that was available at the time was pathetic IMHO.

I just now tried dictating to Dragon Dictation, an iPhone app that is used to allow dictation when the person is not using a computer. The idea is that it will transfer dictation to either Dragon on the PC or MacSpeech Scribe on the Mac for further processing. Unfortunately, I can't get Dragon Dictation to handle more than a short memo. I tried reading Lincoln's Gettysburg address into it (271 words) and it quit way before I was finished on three tries while fiddling with the settings to encourage a longer document. My projects contain 8 or 10 times that many words. The demos indicate that people mostly use it for memos, so I'm running out of viable options if I'm not willing to use the web for my work.
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#22967 - 08/08/12 08:06 AM Re: Current status of speech to text? [Re: JoBoy]
Ira L Offline


Registered: 08/13/09
Loc: California
Originally Posted By: JoBoy

Unfortunately, I can't get Dragon Dictation to handle more than a short memo.


I frequently use Dragon Dictation on the iPhone. True, it is not designed for lengthy dictation, but if you are willing to stop and start, you can have nearly unlimited length dictations. Let the app process two or three paragraphs at a time, then tap the red dictation button, give it a few more paragraphs and repeat. Each restart is appended to where the last one left off. And you can still use the keyboard to edit the output.

Also, on laptop or desktop Macs the built-in dictation feature in 10.8 seems quite good. I just used it to dictate this post.

All in all for lengthy dictation Dragon's Nuance is probably your best bet.
_________________________
On a Mac since 1984.
Currently: 27" iMacs, Macbook Air, macOS 10.14.x,; iPhones, iPods and iPads galore!

Top
#22969 - 08/08/12 09:42 AM Re: Current status of speech to text? [Re: Ira L]
JoBoy Offline


Registered: 08/05/09
Thanks for sharing your experience. It helps. I have a problem where I can't stop and wait for the app to catch up when I'm doing the original speech. That raises the possibility that I'll have to begin with a regular recorder and then transfer it to either Dragon or MacSpeech Scribe for the translation. I'll try to contact Nuance to see what they recommend. Their customer service is very rigid. It seems to me that, just to ask questions, they want all the information you'd give for a purchase, except you don't give them a credit card number.
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#22971 - 08/08/12 11:40 AM Re: Current status of speech to text? [Re: JoBoy]
joemikeb Offline
Moderator

Registered: 08/04/09
Loc: Fort Worth, Texas
FWIW, I have been experimenting with Dictation in Mountain Lion the last few hours, and when using a USB headset microphone in a quiet room, I have been very impressed with its accuracy. However this is again in short bursts of say a paragraph length then pausing to send the data to Apple for conversion to text and waiting for it to come back before proceeding. It appears the limitations I mentioned earlier in relation to my son's medical dictation still hold true here, but the cost — FREE — greatly increases its viability for casual use. I doubt seriously it would be satisfactory in the environment you are wanting.

Out of curiosity, I checked with the new Information Technology director at our church to see what process they use for transcribing the Sunday Sermons and she indicated that after extensive testing both here and at her previous church they still use manual transcriptions. She said the best system they tested — in a situation that appears similar to yours — costs well into five figures and still required extensive manual correction and editing. Even using very expensive commercial grade wireless headphones, if there was background noise such as the organ, or the congregation moving around, the translation accuracy approached zero. tongue
_________________________
joemikeb • moderator

Top
#22974 - 08/08/12 12:11 PM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
Thanks for the info. I've come to the same conclusion. The only hope for my situation would be if I could have recorders whose audio files are compatible with either Dragon12 Premium or MacSpeech Scribe and transcribe well from the recording. I'm in a pinch at work right now, so that will have to wait until I finish today's chores, but I'm still interested. We'll see. So far, the only things that are driving me are Nuance's claims and my hope. I'd like a little evidence before forking out the bucks it will take for that setup. I have a great setup as is, but it involves manual transcribing by someone else and then editing by me. The turnaround time for me hopefully would be faster with the software rather than the manual transcription, but it would involve more of my time and that's a problem, too. On the bright side, I think this discussion can be helpful to others who aren't ready to trust the Cloud concept with their confidentiality obligations. That applies to several professions.
Thanks again for your effort.


Edited by JoBoy (08/08/12 02:36 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#23181 - 08/21/12 10:32 AM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
I called Nuance customer service and asked about my specific recorders. I have two Sony ICD-MX20 recorders. They are each about 1.4" wide, 4.25" long and 0.7" thick. They run on two internal AAA batteries (regular or rechargeable) and also have plugs for external power. They each have a mini microphone that clips to my tie and a small diameter wire that connects the mike to the recorder. I asked the customer service rep if, by any remote chance, my recorders were compatible with the Nuance products. She looked them up on her chart and said that my recorders were one of only two that have a six star rating out of a possible six stars. She said that the recorders they sell only have a five star rating out of six. It blew my mind. Given my stated requirements, she recommended that I use either MacSpeech Scribe($150.00) for the Mac or Dragon Naturally Speaking Premium ($200.00) for the PC (if I want to use it on my VMware/Windows7 setup on my Mac). Dragon Premium has speech dictation functionality as well as transcription of recordings while the MacSpeech Scribe only has transcription of recordings. They're both built on the same engine, but with adaptation for the differences in Mac and PC programming. Since I do 90% of my work on my Mac, I'm likely to get the MacSpeech Scribe for now.

I hope this info is helpful to others. Thanks for your input.


Edited by JoBoy (08/21/12 10:43 AM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#23186 - 08/21/12 06:26 PM Re: Current status of speech to text? [Re: JoBoy]
joemikeb Offline
Moderator

Registered: 08/04/09
Loc: Fort Worth, Texas
let us know how it works in actual practice confused
_________________________
joemikeb • moderator

Top
#23188 - 08/21/12 07:06 PM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
Yessir! It will be a while. Too much going on right now. I don't know what happened to the hazy, lazy days of Summer, but there's nothing hazy or lazy in my corner of the countryside right now.
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#23918 - 10/24/12 11:34 AM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
OK. Here's a long-promised report on the current status of speech-to-text according to my experience. Since I run Windows 7 on VMware on my Mac for a few specific tasks, I had to choose between Dragon Naturally Speaking v12 for Windows and Dragon Dictate 3 for Mac. I chose DNSv12 for Windows for two reasons: (1) Net cost to me to try the software and (2) DNSv12 for Windows is Nuance's flagship offering that is presumably their best foot forward.

The cost issue involved the fact that I already have two Sony ICD-MX20 digital recorders that have worked beautifully for my purposes for a long time AND they have the highest rating for accuracy among recorders that Nuance has tested. The digital voice files have a unique Sony format .msv (memory stick voice). They can be converted to MP3 files using Sony's software, but Dragon Dictate 3 Mac can't use them. It supports MP4 (plus other file formats) and not .msv or MP3.

Dragon Dictate 3 is a new offering that Nuance says is in the ballpark for accuracy with DNSv12, but I don't feel that it has had enough time on the market to establish a credible reputation.

My impression of DNSv12 after using it for one day only to transcribe speeches that were pre-recorded on the Sony units is that it is incredibly accurate for my purposes. Since the speeches are pre-recorded in front of other people, I'm not about to be saying "comma," "period," or "new paragraph." What I get in rough draft form is an accurate capturing of the words of the speech that need formatting and some word correction, but, IMHO it is an amazing result given the inherent variability in the way we speak. This is a huge step forward compared to the earlier version of DNS that I purchased and abandoned several years ago. Compared to the way I have been transcribing the speeches in the past, it is a huge improvement. Setting DNS v12 for maximum accuracy but slowest transcription rate produces a rough draft of two full single-spaced pages in 9 minutes. It takes me longer than that to transfer the .msv file to a flash drive and deliver it to the transcriptionist. It means that I have cut my total production time from a few days to a one-hour turnaround by the time I finish proofing and printing the final copy. I may decide to get a quality microphone and do some dictating, but I'm advised that the quality of the microphone is as important as the quality of the recorder, but, from reviews I have seen, a quality mike with a USB connection is a good way to go. So, at this point, I can't comment on the usefulness of office dictation of emails, memos and longer documents. Nuance's web site has some promotional videos showing these things in action, but I noticed that the persons who do the demonstrations have unusually clear diction. I doubt that I could match their accuracy in dictation. I hope that this is helpful to someone.

Edit: The report to this point appears like an ad for Nuance. There is a downside. It is that they hit you with a vocabulary that they have constructed to describe the various functions and procedures of DNS. It is something of a tech-speak snow job that isn't necessary to get a person doing a garden variety transcription either with a recorder or a microphone. I think they would get more enthusiastic buyers if they first introduced a person to a step by step procedure for getting simple results. Then, they could bring in the bells and whistles. It reminds me of the complexity of Windows as it added functions and grew and grew. For the past few months, I have been using a new iPhone 4S. Most of its functionality is presented in an intuitive way that enables the user to eventually figure most things out with very little help. That device stands in contrast to the complexity of the Nuance introduction to DNS.

Second Edit: In all fairness, they do have a help tab that lays out various topics, but my complaint is that DNS needs an intuitive, simple introduction up front to help the new user get the fundamental concepts and feel success before exposing the person to all the neat stuff with the fancy names.


Edited by JoBoy (10/24/12 02:40 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#23922 - 10/24/12 12:23 PM Re: Current status of speech to text? [Re: JoBoy]
artie505 Online


Registered: 08/04/09
It doesn't help me other than by its having taught me something.

Many thanks for the clear, concise, in depth analysis. smile
_________________________
The new Great Equalizer is the SEND button.

In Memory Of Harv: Those who can make you believe absurdities can make you commit atrocities. ~Voltaire

Top
#23924 - 10/24/12 01:15 PM Re: Current status of speech to text? [Re: JoBoy]
joemikeb Offline
Moderator

Registered: 08/04/09
Loc: Fort Worth, Texas
While you are at it how about a comparison between Dragon Naturaloy Speaking for Windows and Drago Dictate 3 for Mac? grin

Seriously — thanks for the review.
_________________________
joemikeb • moderator

Top
#23926 - 10/24/12 01:25 PM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
Walt Mossberg did a review on Dragon Dictate 3. Here's the link. If it could have handled my Sony's files, I probably would have jumped for it, but it couldn't.

http://allthingsd.com/20121009/a-dragon-that-takes-dictation-and-controls-a-mac-by-voice/
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#24143 - 11/12/12 08:19 AM Re: Current status of speech to text? [Re: JoBoy]
JoBoy Offline


Registered: 08/05/09
WARNING! In my opinion, after having spent two weeks trying to get it to function normally, Dragon Naturally Speaking v12 Premium on Windows 7 on VMware Fusion3 on Mac 10.6.8 will not work and is a hazard to patience, good will and general well being!

Although my preliminary remarks above were encouraging, they were preliminary and did not prove to be accurate as I sought to gain reasonable functionality. I do not recommend this combination. Nuance's phone system that tries to solve everything by automated messages requires the patience of Job to reach a human being. I even obtained an installation DVD to reinstall after my poor experience with the original installation via Internet download. The DVD wouldn't install. It was pathetic. Finally, a tech assistance person told me that DNS doesn't work on my configuration and that DNS needs the PC hardware to work properly. This was in direct contradiction to what I was told by the sales person when I made the purchase.
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#24150 - 11/12/12 11:13 AM Re: Current status of speech to text? [Re: JoBoy]
joemikeb Offline
Moderator

Registered: 08/04/09
Loc: Fort Worth, Texas
Thanks for getting back with a followup report. I am disappointed but I am sure not as much as you are.
_________________________
joemikeb • moderator

Top
#24151 - 11/12/12 11:28 AM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
Yeah. That was a real letdown. Frankly, I was suckered by an over-enthusiastic sales person.

I'm so sick of Nuance that I can't even think of trying Dragon Dictate 3 even if Walt Mossberg praises it.
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#24324 - 11/27/12 07:26 PM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
UPDATE:
I received Dragon Dictate v3 for the Mac today. It's like a different world compared to the problems associated with DNSv12. For lack of a better term, DD3 is, well..., more Mac-like. Installing on Mountain Lion 10.8.2 was a breeze. DD3 offered a tutorial which I followed carefully. It had none of the extraneous clutter that DNS has accumulated. Using the included microphone, I went through the tutorials where the app becomes acquainted with my speech. They required only one voice training exercise, but I went through all four voice training exercises plus the one they use to demo how it's done. I did this because my recorded speeches contain a lot of jargon and I expected to have difficulty training DD3 to get things right. After surviving the tutorial and voice training, I used the included microphone and read aloud one of the speeches I made a while ago just to see how it would turn out using dictated words instead of recorded words. I didn't dare to look at it until I finished dictating. This was my first attempt at dictating a document, so I did not attempt to do much punctuating.

I have to admit that the result was nothing short of amazing!. There were only a very few errors. The punctuation was not perfect because I haven't learned to punctuate while dictating, but DD3 did a very creditable job just guessing where the periods, commas and apostrophes should be. it will continue to be an issue when I transcribe recorded speech, but I'm not worrying about it now because DD3 by itself gets punctuation right most of the time. The spelling was incredibly good--better than my pronunciation deserved. I could not hope to have a better result. Having undergone some of the training on DNSv12, I can say that, in my opinion, I was grossly misled by the sales person who assured me that DNSv12 would work on Windows7 via VMware on a Mac. The experience I've had today is really encouraging. I can't wait to receive the digital recorder that produces recordings that are compatible with DD3 on the Mac. UPS sent me a notification today that they had a problem and the package won't arrive until Thursday or Friday. That's when the rubber meets the road for me. Hopefully, it will be a result that will encourage others to jump in. I first bought a Nuance product, version 9 for Windows in 2006 that I used on a Dell PC. That was a flop. I then suckered for DNSv12 about six weeks ago and that was a flop because I was over-sold by the sales person. This third try is looking very good, but I'll hold the celebration until I see how it works with the recorder. Thanks for your patience and sympathy.


Edited by JoBoy (11/27/12 07:55 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#24346 - 11/30/12 09:37 AM Re: Current status of speech to text? [Re: joemikeb]
JoBoy Offline


Registered: 08/05/09
I've now made recordings on the Sony ICD-UX523. It produces .wav and a variety of mp3 formatted recordings for the Mac. I bought it for the uncompressed .wav output. It has been necessary to do separate Voice Training on Dragon Dictate3 for the Mac for the recorded input to DD3. The Voice Training profile I did for microphone input didn't recognize the recorder's input. It was hilarious gibberish.

The last hurdle before putting the pieces together for the project was to select a recorder that produced output for the Mac. I preferred an uncompressed file in the hope that it would yield a more accurate result. This was discussed in a separate topic on FineTunedMac called: Re: Are LPCM and .wav audio formats virtually the same? I'm grateful for the assist on that topic.

In the preliminary work, the results are quite good. Now that I have the routine in mind, I'm going to adjust some of the recorder's settings and see if I can improve things a bit. Frankly, I'm nearly satisfied by the current results, but I do want to see if I can make it a little more accurate.

Later:
I lowered the sensitivity of the microphone to "Low." This tends not to incorporate as much background hum. The results were VERY good. I'm thrilled. Finally, after all these years and two flops, I have a transcription system that actually does the job! Thanks to all for the advice and sympathy. It all helped. In my recent experience, Dragon Dictate for Mac v3.01 does the job and is worth the effort.

Don't get discouraged by your initial results. The digital recorder transcriptions are likely to be gibberish and nonsensical if you haven't trained the recorder profile (use "Digital In" on the recorder profile). Line In did not yield the same quality transcription in my experience. You do need to train separate profiles for microphone command work and for transcription of digital recorder files. I recommend using the .wav format to enhance accuracy, but I'm saying that based upon instinct and not experience. The recorder I bought has .wav and several versions of .mp3 (different compression features). DD3 doesn't use .mp3. I'm thrilled with the recorder. It replaces an old Sony ICD recorder that just died after several years.


Edited by JoBoy (11/30/12 04:05 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top
#28874 - 05/02/14 03:53 AM Re: Current status of speech to text? [Re: JoBoy]
deniro Offline


Registered: 09/09/09


Edited by deniro (05/02/14 04:38 AM)
_________________________
OS X 10.11.6
iMac 21.5", Mid 2011
2.8 GHz Intel Core i7, 24 GB
AMD Radeon HD 6770M
Using Apple computers since 1980

Top
#28875 - 05/02/14 04:23 AM Re: Current status of speech to text? [Re: JoBoy]
deniro Offline


Registered: 09/09/09
Last week I bought a Sony ICD-AX412 voice recorder for $70 with a $10 coupon from OfficeMax.

The included Sound Organizer software is incompatible with the Mac, but I was able to transfer files back and forth between the mac and recorder without any problem with the USB cable which is included. I could change the names of files and folders, which is all I would need anyway, if even then. I don't know yet. Too early to tell. You can arrange files and folders on the recorder itself.

Be sure to check the specs in the manual very carefully, cover to cover, regarding system requirements and so on, as you know. These manuals have lots of small print, asterisks, and exceptions.

The default format for files is mp3. You can record in 192k stereo, 128k stereo, 48k mono, or 8K mono. I was impressed by the quality of the recordings using the built-in mic, though this is the first voice recorder I have used in at least fifteen years when they were microcassette. Things have changed quite a bit since then. On the current recorder's playback, I noticed the popping of Ps. I dont know if that is my fault or the recorder's.

I wonder how voice recognition software would handle my midwestern mumble.

The recorder's packaging box says, in blurb fashion, "Compatible with Dragon Naturally Speaking" but just now when I perused the manual I couldn't find any mention of that. Google, as you know.

http://thewirecutter.com/reviews/the-best-voice-recorder/


Edited by deniro (05/02/14 04:29 AM)
_________________________
OS X 10.11.6
iMac 21.5", Mid 2011
2.8 GHz Intel Core i7, 24 GB
AMD Radeon HD 6770M
Using Apple computers since 1980

Top
#28876 - 05/02/14 04:24 AM Re: Current status of speech to text? [Re: joemikeb]
deniro Offline


Registered: 09/09/09
In post 22947, how did you make the dotted, indented list?
_________________________
OS X 10.11.6
iMac 21.5", Mid 2011
2.8 GHz Intel Core i7, 24 GB
AMD Radeon HD 6770M
Using Apple computers since 1980

Top
#28877 - 05/02/14 04:29 AM Re: Current status of speech to text? [Re: deniro]
artie505 Online


Registered: 08/04/09
Go back to that post and hit the "Quote" button, which will reveal the raw formatting.
_________________________
The new Great Equalizer is the SEND button.

In Memory Of Harv: Those who can make you believe absurdities can make you commit atrocities. ~Voltaire

Top
#28896 - 05/03/14 06:52 PM Re: Current status of speech to text? [Re: deniro]
JoBoy Offline


Registered: 08/05/09
I checked Sony's web site to see if your recorder Sony ICD-AX412 is compatible with the Apple OS X operating system. The answer was: "There are no files available to download for the selected operating system." That means no compatibility. I had two Sony ICD-MX20 recorders that are not Mac compatible. When I look them up for Mac compatibility, Sony doesn't even mention Mac--only Windows info is shown. I tried what you are doing, but things just didn't function properly with Dragon Dictate3. Some of that is mentioned above in this thread. When I realized that Dragon Naturally Speaking doesn't work on VMware/Windows7, I decided to go with Dragon Dictate3. I was able to get a refund from Nuance that paid for Dragon Dictate3. I did a lot of Internet shopping for Mac compatible recorders and came up with this Sony configuration:

The Sony recorder that I purchased was a Sony ICD-UX523 Digital Flash Voice Recorder. It is available on Amazon right now for $95.77 Sony's website answer for this model is: "This model of voice recorder is compatible with Apple® Macintosh® computers installed with the following operating systems:

Mac OS X v10.2.8 (Jaguar) -*Must be version 10.2.8. Earlier versions of Jaguar are not supported.
Mac OS X v10.3 (Panther)
Mac OS X v10.4 (Tiger)
Mac OS X v10.5 (Leopard)
Mac OS X v10.6.7 (Snow Leopard)
Mac OS X v10.7 (Lion)
Mac OS X v10.8 (Mountain Lion)
Mac OS X v10.9 (Mavericks)
NOTE: The software supplied with the recorder is not compatible with Macintosh computers."

You don't need the incompatible software included in the package with the recorders.

I also purchased a Sony ECM-CS10 Tie-Clip-Style Omnidirectional Business Microphone (available on Amazon for $32.98 right now.) This is an excellent microphone that enables the recorder to shine with Dragon Dictate3. I always select the LPCM (.wav) file format for best results recording speech that will be transcribed to text.

Obviously, your intended use will dictate whether you need to purchase this combination, but I can tell you from personal experience over the last two years that this is the equipment that works for me with maximum results. Be sure to follow Nuance's directions for voice training, vocabulary training and profiles. That's how DD3 gets used to your "accent." We all have an accent and need to help the machine to understand us.

Also, I don't use any punctuation in the input I give the machine. I'm giving a speech and it would annoy the listeners and distract me. The result is a string of words with no punctuation on the initial pages. You do punctuation on an rtf file by entering "Command-S" after the transcription is completed. I copy the rtf file to InDesign, an Adobe app that enables me to precisely place the words where needed in various boxes. I do this because of special uses that require this. For normal stuff, the rtf file is just fine or you can copy and paste into Word.

Obviously, your decision to purchase or not depends upon your intended use and how urgent that use is for you. All I ask is that, if you decide to go for it, DO SO AT YOUR OWN RISK. I can almost guarantee that, at some points along the way, you will become very irritated at the clumsy way some things are done. I want you to curse Nuance and not me. The only thing that has enabled me to reach my level of enjoyment of the system I now have is PERSISTENCE! I wish it were easier and I sometimes wonder if it was worth the effort. I don't know anything about Dragon Dictate 4. I'll probably look into it, but I hesitate to disturb my current working setup that was achieved by expending a lot of time and effort.


Edited by JoBoy (05/03/14 06:58 PM)
_________________________
Mac Pro dual Quad-Core Intel Xeons Early 2008; 16GB RAM; MacOS X 10.11.6, iOS 9.3.5

Top

Moderator:  alternaut, dianne, dkmarsh