Technology


I’ve been looking for a way to use speech recognition to automate the transcription of interviews, meetings, speeches, conference presentations, and so on.

I spend a lot of time on the phone interviewing experts for the articles and reports I write. Normally I conduct the interview with a headset and do my best to type a transcript of what is said. I’m slow and a terrible typist, so my transcript misses a lot and comes out with many misspellings that are impossible to correct. Usually for an hour-long interview it takes me another hour to go through and fix mistakes, filling in gaps, and making guesses at uninterpretable words.

I would greatly benefit from a speech recognition solution that could create a fairly accurate transcript from audio, for example, live over the phone or from an mp3 file.

This need was emphasized to me even more this week, when I attended a conference and spent two days trying to take notes and capture useful quotes from speakers. I have a digital voice recorder and have all of the presentations in mp3 format, but it’s going to be quite a challenge to comb through all of that audio to find relevant quotes for the articles I will be writing about the conference. How much easier it would be it I had a software application that could convert all of those mp3s into fairly accurate text transcripts!

Unfortunately, it appears that voice recognition software is not ready to handle meetings and so on where multiple voices are involved. These systems have to be trained to recognized the voice of a single user.

I’m using this blog post to mark and share some possible solutions I have encountered. I will plan to add to this list as time goes — if and when the technology continues to improve.

+ Dragon Naturally Speaking by Nuance is supposed to be the best reasonably-priced speech recognition software for professional use. Nuance says Dragon is not able to transcribe multiple voices, but I’m tempted to shell out the $200 just to see what kind of results I might get with it. Suppose it were 50 percent accurate transcribing unfamiliar voices? That might be good enough for me.

+ Windows has its own built-in speech recognition capability. I plan to test this out to see whether I can make it work somehow. However, it’s hard to believe that Microsoft could come up with a better solution than a specialist company like Nuance.

+ One suggestion I’ve run into a lot is to transcribe a meeting or lecture by “parroting” or “re-speaking.” In other words, using speech rec software like Dragon, you listen to the recording of the meeting on headphones and repeat what you hear into your computer mic. Because Dragon is trained to your voice, it can create an automatic transcript. Sounds laborious, but it would probably be better that having to type it all out myself.

+ I also heard about a company called Koemei that has a cloud-based solution for converting video and audio assets into text. Looks as if this might work pretty well, however, their entry-level service is $149 per month. That sounds like a lot, but maybe someday…. For $20 per month I would definitely try it.

+ Another idea I have thought of is to call my Google Voice number and play the audio recording into my voicemail. Google Voice automatically transcribes my voicemails into text and often does an acceptable job — good enough so I could paste the results into a word processor and make quick corrections. I’m not sure yet if Google Voice can handle long audio streams, though. I’m thinking about testing this solution to see if I can make it work somehow.

+ Here’s an interesting video by Chaelaz showing how to use YouTube’s closed-captioning transcription service to convert audio to text. Looks as if you would have to create a video first and upload it to YouTube, but that’s an interesting possible work-around for what I’m trying to do.

ARB — 21 June 2013

Advertisements

Wire rope transmission in 1896. Source: Stadtarchiv Schaffhausen.

Kris De Decker at  Low-tech Magazine has published a fascinating article discussing rope drives, a 19th-century technology that was used, especially in Europe, to transmit power over shorter distances. This method of transmission was actually “more efficient than electricity for distances up to 5 kilometres” and even today “would be more efficient than electricity over relatively short distances.”

De Decker makes an interesting connection to the spread of small-scale renewable energy production and suggests a possible role for a technology such as the endless rope drive:

“In spite of [some drawbacks discussed in the article], power transmission by ropes might have a place in our energy systems. Today, there is a trend towards small-scale, decentralized power production, based on renewable energy sources. These solar panels, water turbines or wind turbines generate electricity, but whenever we need to produce mechanical energy, eliminating the step of generating electricity could result in a somewhat less practical, but more efficient use of energy.”

De Decker thinks that “If we used modern materials for making ropes and pulleys, we could further improve this forgotten method.” He illustrates his article with many photos of 19th-century installations.

ARB — 4 April 2013

I just heard a fascinating interview with sculptor and stop-motion animator John Frame, who explained how his long-term project “The Tale of the Crippled Boy” came to him in a dream. Frame had been a sculptor for decades but had hit a creative wall, or more precisely had run out of steam, to use another metaphor. He had reached a point in his creative work where he just couldn’t create anymore.

Then one night he had a lucid dream in which he imagined an entire world populated with characters in motion. He somehow recognized that these characters were his own creations, and in that dream state he spent several hours observing this world. When when he woke up early in the morning, he captured it all in drawings and notes and storyboards and began his current stop-motion animation project. Did I mention that he had never done stop-motion before? But now “The Tale of the Crippled Boy” has become his entire creative activity.

You can see Frame’s initial animations here on Vimeo:

I have to admit that I’m not drawn to the creative product, fascinating and detailed as it is — too bizarre to appeal to me. But what I am intrigued by is the way the idea came to the creator — seemingly arriving out of the blue in a dream state. Everybody dreams, and I suspect that lucid dreaming is fairly common. However, the important thing here is that Frame got up and captured it all so he could turn the idea into a creative product. It’s also significant that the stop-motion product draws on his many years of work as a sculptor.

This experience illustrates what I think are some important lessons about the creative process, and it follows the ideas set out in my favorite book on this topic — A Technique for Producing Ideas, by James Webb Young. Written in 1965, this is a brilliant treatise for anyone involved in creative work — Young was actually an advertising guy, but his ideas really apply to anyone in the arts. It’s only 36 pages. You can buy it for a few dollars on Amazon and read it in an hour or so.

Thinking about Young’s book and John Frame’s experience, here are some lessons I extract:

  1. Work very hard over the long term to develop your creative skills, whatever they are — design, writing, drawing, sculpture, painting, music — or skills that are creative but more commonly used in the business world, such as copywriting, graphic design, or art direction. I would also extend this lesson into areas such as innovation, science, engineering, and architecture.
  2. When you are up against a creative problem, put a lot of concentrated effort into analyzing the problem, doing research, brainstorming, testing ideas.
  3. When you are sick and tired of all that concentrating, take a break for an hour, a day, a week, or even longer. Do something else. Relax. Exercise. Go for a hike. Watch a movie. Read. Or go to sleep.
  4. At an unexpected moment an idea or a series of ideas will come to you. Be prepared to capture these ideas — have the tools you need always available to write down or draw out ideas that come to you. I always carry a pocket notebook and set of pens with me. Ideas often come to me when I’m out walking. Like Frame, ideas have sometimes come to me in dreams or just before sleeping or just upon waking up.
  5. After the idea comes to you, work with it and adjust it and figure out how to make it work in a practical way. It might be the solution to the problem you’ve been working on, or it might be the source of an entirely new and unexpected creative endeavor.

You can hear the interview with John Frame at The Story — his is the second part of that particular show.

ARB — 14 Oct. 2012

Today a telemarketer from AT&T interrupted my workday (even though I’m on the do-not-call list) and offered to sell me a triple-play bundle of digital TV, Internet, and phone. When I asked him if AT&T offered digital TV in my neighborhood, he looked it up and said no. Way to go, AT&T.

AB — 10 May 2012

 

I thought this was an interesting and useful infographic highlighting the growing U.S. solar manufacturing business. Right now, it shows a $5.6 billion industry that imports $3.75 billion, for a $1.9 billion trade surplus.

I wrote something about the growth of the solar industry recently for ThomasNet Green & Clean — see “How Will U.S. Army Energy Initiatives Affect Expansion of Solar Energy?

Infographic shows US solar industry trade surplus

AB — 15 September 2011

 

Fascinating cartoon from xkcd. Think he really did this? Would it work? He doesn’t say whether the effect works with objects farther away, such as the moon. Probably not. (The full image doesn’t fit here — click through to see the original.)

Instructions for setting up a 3D sky viewer

AB — 22 August 2011

Next Page »