Speech-Recognition for Interviews

Every day, we get phone calls and e-mails from people hoping to use speech recognition software to transcribe interviews, lectures, or meetings. It seems so reasonable to assume that today's technology could easily take a digital voice recording of two or more people and translate that into an accurate text representation.

Sadly, that is not the case. The supercomputers of the CIA and NSA notwithstanding, today's most popular voice to print software programs are unable to translate the speech of more than one person with any degree of real usability for several reasons:

1. Speech recognition software should be trained for the speaker's voice. While Dragon NaturallySpeaking promotes that "no training is necessary," allowing the software to adapt its algorithms to the speakers voice, speaking style, and writing style can tremendously improve the accuracy of the software.
2. It is impossible for speech recognition software to discern the difference speakers in a recorded conversation. To the computer all sounds are analyzed to find signs of spoken words. The software can not, at one moment, recognize Speaker A and the next moment recognize Speaker B. It will try to decipher all spoken words using whatever singular user profile has been selected in the software for transcribing.
3. Speech recognition software is really a dictation tool, rather than a transcription device. That is to say, it works best when the speaker "dictates" to the software. Accurate dictation includes punctuation, spellings of potentially unknown words or names, and uses complete sentences and phrases. When was the last time you heard two people talking together in complete sentences, and speaking intended punctuation?
   

I'm using speech-recognition software to write this blog. Before I dictate, I formulate the sentences mentally, then speak them evenly and with punctuation into my wireless headset. Almost instantly, the phrase I have just completed appears as text on the screen. And with amazing accuracy. The accuracy is due to the fact that I trained my speech recognition software (in this case MacSpeech Dictate) to understand how I dictate.

Speech recognition software works amazingly well. But, for its intended purpose.

There have been some of our customers who have employed creative workarounds for the purpose of converting interviews to text without typing. One of the most common we hear of, is where the interviewer listens to a recording of the interview in one ear, and dictates what they hear into the speech recognition software. This gives them the ability to add subject names and formatting instructions lacking in the original recording. This method also helps clarify the conversation where both parties were talking at the same time (you can imagine how inaccurate any type of automated transcription would be).

As technology pushes the limits of power and speed in personal computers, we should someday expect to see speech recognition systems that come close to replicating the recognition capabilities of the human brain. Realizing the an enormous capacity and sophistication of our brains, I cannot imagine that happening anytime soon.

Technorati Profile

Finally, Great Speech Recognition for the Mac

Fans of Dragon NaturallySpeaking have long enjoyed the convenience of writing with their voice. Voice to print software makes it easy, convenient, and more comfortable for those of us who tire of typing long tomes.

While speech recognition software for the Macintosh has been around for a long time, it is never been the workhorse that Dragon NaturallySpeaking has been for the PC world.

That has all changed today. Announced at this year's MacWorld Expo in San Francisco, Dictate from MacSpeech has been one of the most long-awaited new programs for the Macintosh platform. The first booth I visited at MacWorld in January was the MacSpeech booth. I was handed a wireless microphone and asked to give it a whirl. Having experienced the more cumbersome iListen product, the accuracy and speed of the Dictate product simply floored me.

This past week I received my copy of Dictate. In fact, I am writing this blog using my voice. To be sure, it is making a few minor mistakes. It has had little chance to learn how I talk, or for me to learn how to talk to it. But all in all, its accuracy "out-of-the-box" appears to be better than 98%. And, that is amazing.

MacSpeech Dictate is built on top of the same engine used for Dragon NaturallySpeaking. MacSpeech licensed the technology from Nuance and has done an admirable job of adapting the platform to the Macintosh interface. This first version still lacks some of the more advanced features of Dragon NaturallySpeaking; however, its speed and accuracy -- the two most important features of any speech recognition software -- make this program an almost "must-have" for every Macintosh aficionado.

As many of you know, we are Macintosh experts. I have been using Macintosh computers since the very first Mac plus in 1984. Although I used PCs everyday to provide technical support for our customers, I've always enjoyed the ease, style, and performance of Apple computers.

MacSpeech Dictate now moves the entire Macintosh platform one step closer to equal par with Windows computers in terms of software application availability.

We are now offering MacSpeech Dictate on our website. We are still assembling the product information, documentation, and images shoppers have come to rely upon when visiting our site. One of the things we're most adamant about when adding new products to our offering, is that we know and understand how the products work. We never want to offer products we cannot stand behind or support.

For those of you who already own MacSpeech iListen, there is an upgrade available.

By the way, I am dictating this blog using a wireless USB headset, the Plantronics CS 50. I've used this headset often for Dragon NaturallySpeaking, and was curious how well it would perform with MacSpeech Dictate. Well, as they say, "the proof is in the pudding." I'm having no difficulty at all dictating this piece using the CS 50 headset.

There's still more for me to learn about this program, but if you're considering adding speech recognition to your Macintosh, for free to give me a call, toll-free, at 866-408-1383.

One more thing: MacSpeech Dictate does require the use of one of the new Intel Macs. Like Dragon NaturallySpeaking, MacSpeech Dictate requires a significant amount of processing power. I'm using it on my book Pro, 2.4 GHz Intel.

(Editor Note: I just proofed what I dictated and found 12 errors made by Dictate. Out of 563 words, that equals a 97.87% accuracy.)