Category Archives: Writing

A Brief History of ASR: Automatic Speech Recognition

Dear readers, I apologize for the month long hiatus but I assure you that it was much needed. Today’s post is a guest post. If you’re interested in writing one of these, please reach out to me via my contact page here.

This article is originally published at Descript.

This moment has been a long time coming. The technology behind speech recognition has been in development for over half a century, going through several periods of intense promise — and disappointment. So what changed to make ASR viable in commercial applications? And what exactly could these systems accomplish, long before any of us had heard of Siri?

The story of speech recognition is as much about the application of different approaches as the development of raw technology, though the two are inextricably linked. Over a period of decades, researchers would conceive of myriad ways to dissect language: by sounds, by structure — and with statistics.

Early Days

Human interest in recognizing and synthesizing speech dates back hundreds of years (at least!) — but it wasn’t until the mid-20th century that our forebears built something recognizable as ASR.

1961 — IBM Shoebox

Among the earliest projects was a “digit recognizer” called Audrey, created by researchers at Bell Laboratories in 1952. Audrey could recognize spoken numerical digits by looking for audio fingerprints called formants — the distilled essences of sounds.

In the 1960s, IBM developed Shoebox — a system that could recognize digits and arithmetic commands like “plus” and “total”. Better yet, Shoebox could pass the math problem to an adding machine, which would calculate and print the answer.

Meanwhile researchers in Japan built hardware that could recognize the constituent parts of speech like vowels; other systems could evaluate the structure of speech to figure out where a word might end. And a team at University College in England could recognize 4 vowels and 9 consonants by analyzing phonemes, the discrete sounds of a language.

But while the field was taking incremental steps forward, it wasn’t necessarily clear where the path was heading. And then: disaster.

October 1969 The Journal of the Acoustical Society of America

A Piercing Freeze

The turning point came in the form of a letter written by John R. Pierce in 1969.

Pierce had long since established himself as an engineer of international renown; among other achievements he coined the word transistor (now ubiquitous in engineering) and helped launch Echo I, the first-ever communications satellite. By 1969 he was an executive at Bell Labs, which had invested extensively in the development of speech recognition.

In an open letter³ published in The Journal of the Acoustical Society of America, Pierce laid out his concerns. Citing a “lush” funding environment in the aftermath of World War II and Sputnik, and the lack of accountability thereof, Pierce admonished the field for its lack of scientific rigor, asserting that there was too much wild experimentation going on:

“We all believe that a science of speech is possible, despite the scarcity in the field of people who behave like scientists and of results that look like science.” — J.R. Pierce, 1969

Pierce put his employer’s money where his mouth was: he defunded Bell’s ASR programs, which wouldn’t be reinstated until after he resigned in 1971.

Progress Continues

Thankfully there was more optimism elsewhere. In the early 1970s, the U.S. Department of Defense’s ARPA (the agency now known as DARPA) funded a five-year program called Speech Understanding Research. This led to the creation of several new ASR systems, the most successful of which was Carnegie Mellon University’s Harpy, which could recognize just over 1000 words by 1976.

Meanwhile efforts from IBM and AT&T’s Bell Laboratories pushed the technology toward possible commercial applications. IBM prioritized speech transcription in the context of office correspondence, and Bell was concerned with ‘command and control’ scenarios: the precursors to the voice dialing and automated phone trees we know today.

Despite this progress, by the end of the 1970s ASR was still a long ways from being viable for anything but highly-specific use-cases.

This hurts my head, too.

The ‘80s: Markovs and More

A key turning point came with the popularization of Hidden Markov Models(HMMs) in the mid-1980s. This approach represented a significant shift “from simple pattern recognition methods, based on templates and a spectral distance measure, to a statistical method for speech processing”—which translated to a leap forward in accuracy.

A large part of the improvement in speech recognition systems since the late 1960s is due to the power of this statistical approach, coupled with the advances in computer technology necessary to implement HMMs.

HMMs took the industry by storm — but they were no overnight success. Jim Baker first applied them to speech recognition in the early 1970s at CMU, and the models themselves had been described by Leonard E. Baum in the ‘60s. It wasn’t until 1980, when Jack Ferguson gave a set of illuminating lectures at the Institute for Defense Analyses, that the technique began to disseminate more widely.

The success of HMMs validated the work of Frederick Jelinek at IBM’s Watson Research Center, who since the early 1970s had advocated for the use of statistical models to interpret speech, rather than trying to get computers to mimic the way humans digest language: through meaning, syntax, and grammar (a common approach at the time). As Jelinek later put it: “Airplanes don’t flap their wings.”

These data-driven approaches also facilitated progress that had as much to do with industry collaboration and accountability as individual eureka moments. With the increasing popularity of statistical models, the ASR field began coalescing around a suite of tests that would provide a standardized benchmark to compare to. This was further encouraged by the release of shared data sets: large corpuses of data that researchers could use to train and test their models on.

In other words: finally, there was an (imperfect) way to measure and compare success.

November 1990, Infoworld

Consumer Availability — The ‘90s

For better and worse, the 90s introduced consumers to automatic speech recognition in a form we’d recognize today. Dragon Dictate launched in 1990 for a staggering $9,000, touting a dictionary of 80,000 words and features like natural language processing (see the Infoworld article above).

These tools were time-consuming (the article claims otherwise, but Dragon became known for prompting users to ‘train’ the dictation software to their own voice). And it required that users speak in a stilted manner: Dragon could initially recognize only 30–40 words a minute; people typically talk around four times faster than that.

But it worked well enough for Dragon to grow into a business with hundreds of employees, and customers spanning healthcare, law, and more. By 1997 the company introduced Dragon NaturallySpeaking, which could capture words at a more fluid pace — and, at $150, a much lower price-tag.

Even so, there may have been as many grumbles as squeals of delight: to the degree that there is consumer skepticism around ASR today, some of the credit should go to the over-enthusiastic marketing of these early products. But without the efforts of industry pioneers James and Janet Baker (who founded Dragon Systems in 1982), the productization of ASR may have taken much longer.

November 1993, IEEE Communications Magazine

Whither Speech Recognition— The Sequel

25 years after J.R. Pierce’s paper was published, the IEEE published a follow-up titled Whither Speech Recognition: the Next 25 Years⁵, authored by two senior employees of Bell Laboratories (the same institution where Pierce worked).

The latter article surveys the state of the industry circa 1993, when the paper was published — and serves as a sort of rebuttal to the pessimism of the original. Among its takeaways:

  • The key issue with Pierce’s letter was his assumption that in order for speech recognition to become useful, computers would need to comprehend what words mean. Given the technology of the time, this was completely infeasible.
  • In a sense, Pierce was right: by 1993 computers had meager understanding of language—and in 2018, they’re still notoriously bad at discerning meaning.
  • Pierce’s mistake lay in his failure to anticipate the myriad ways speech recognition can be useful, even when the computer doesn’t know what the words actually mean.

The Whither sequel ends with a prognosis, forecasting where ASR would head in the years after 1993. The section is couched in cheeky hedges (“We confidently predict that at least one of these eight predictions will turn out to have been incorrect”) — but it’s intriguing all the same. Among their eight predictions:

  • “By the year 2000, more people will get remote information via voice dialogues than by typing commands on computer keyboards to access remote databases.”
  • “People will learn to modify their speech habits to use speech recognition devices, just as they have changed their speaking behavior to leave messages on answering machines. Even though they will learn how to use this technology, people will always complain about speech recognizers.”

The Dark Horse

In a forthcoming installment in this series, we’ll be exploring more recent developments and the current state of automatic speech recognition. Spoiler alert: neural networks have played a starring role.

But neural networks are actually as old as most of the approaches described here — they were introduced in the 1950s! It wasn’t until the computational power of the modern era (along with much larger data sets) that they changed the landscape.

But we’re getting ahead of ourselves. Stay tuned for our next post on Automatic Speech Recognition by following Descript on Medium, Twitter, or Facebook.

Timeline via Juang & Rabiner

This article is originally published at Descript.

Regina Bethory is a fiction author. She graduated from Christopher Newport University with a Bachelor’s in Directing and Play Writing and from Newport News Shipbuilding’s Apprentice School as a Test Electrician. She also has a degree in Funeral Services. As an avid minimalist and traveler, she enjoys spending her time learning new things, seeking new experiences and de-cluttering. When she is not writing, she can often be found in comic book stores and early morning matinees.

The Top 6 Benefits of Writing

Hello, readers! My week hiatus from writing after that really intense month was bittersweet. On one hand, I felt that I was burning out at the end of July and needed a break. On the other hand, this past week has been one of the most emotional and stressful weeks I’ve experienced in a long time. At first I thought that it was just a weird phase. However, I have read in the past about how beneficial writing can be to one’s mental health. It prompted me to do some more research. Below, I have listed what my experience has led me to believe are the top 6 benefits of writing.

The Top 6 Benefits of Writing

1. Relaxation/Eliminates Stress

By getting my thoughts out on paper, I can unwind from the work day or get my ducks in a row for the day ahead. Writing helps me vent all of my frustrations or reflect on what I’m grateful for. It can also helps me put my struggles into perspective.

2. More Productive/Wakes Me Up

When I wake up a little earlier to get my morning pages done or work on my blog, I feel more productive. It allows me to start the day off right and wake my brain up before the commute to work. It helps me feel like I’ve accomplished something.

3. Learning New Things/Establishing Community

Whether it’s expanding your vocabulary, or learning about new topics by researching things you want to write about, writing helps you learn! Last month I was constantly learning. I was also constantly reading and connecting with other writers and bloggers.

4. Helps Memory

Writing is a mental exercise. It trains your brain in so many ways. You can stockpile ideas before you lose them or store memories from trips. I know I don’t want to forget that 7-course sushi dinner we had in D.C. or the artful displays of Fish Bone Alley in Gulfport, Mississippi (blog post to come). Some people use it to record their dreams and they end up finding it much easier to remember them when they wake up, after practice.

5. Better Sleep

Feeling grateful for my life, relaxing from a hectic day and getting my emotions down on paper can ease my mind into sleep faster. I sleep better when I write. And better sleep is never a bad thing!

6. Faster Typing/Writing Skills

At my day job I’m often teased because of my fast typing rate. People are always amazed, especially when I can type quickly without looking at the keyboard. When they ask how I do it, the answer is simple. It’s the same way you get to Carnegie Hall. Practice. Practice. Practice. (That was a theater joke).

Still don’t believe me? Check out this fantastic blog post by Gregory Ciotti on the psychological benefits of writing: https://www.helpscout.net/blog/benefits-of-writing/

Happy Writing!

-RB

Regina Bethory is a fiction author. She graduated from Christopher Newport University with a Bachelor’s in Directing and Play Writing and from Newport News Shipbuilding’s Apprentice School as a Test Electrician. She also has a degree in Funeral Services. As an avid minimalist and traveler, she enjoys spending her time learning new things, seeking new experiences and de-cluttering. When she is not writing, she can often be found in comic book stores and early morning matinees.

July Camp NaNoWriMo 2018: Blog Challenge Complete

Dear readers, the July Camp NaNoWriMo 2018 has come to an end and with it, my self-imposed blog-a-day challenge. I have to say, when I first got the idea for this challenge it was about three days before the start of July. It seems like yesterday. I was so afraid that I wouldn’t be able to keep up or that I’d run out of ideas. However, thanks to a remarkable camp cabin and all of you, I’ve been able to persevere.

What I Learned During July Camp NaNoWriMo 2018

Above all, I learned that I am more than capable of writing over 50,000 words in a month. In fact, much like my high school years of running cross country, I find myself crossing the finish line thinking that I could have pushed myself harder. There were nights I came home from work and the last thing I wanted to do was sit in front of a computer screen, but I found a way. There were days that I could’ve gotten ahead by writing multiple blog spots in spare time, but I didn’t.

This month has proved to me the importance of the phrase “slow and steady wins the race.” Too often do I have the notion set in my head that I can sit down and dictate an entire novel’s rough draft in a weekend. While I’m sure it’s possible, it wouldn’t be the greatest to edit. There is something very satisfying about seeing that NaNoWriMo progress bar go up a little each day. (I’ve been trying to create my own spreadsheet in MS Excel to track my words off-season. Any suggestions are appreciated in the comments below!)

Overall, I had a blast this month and proved to myself that I am capable of accomplishing what I set my mind to. While it’s something that I’ve been aware of before, sometimes we all need a little reminding.

What’s Next?

While I do plan to regularly post on my blog, going forward I will no longer be posting every single day. I’m sure my subscribers will be thankful to give their inboxes a break! I do look forward to spending more time on my fiction and sharing pieces with my patrons.

At the end of August, my novel, In Articulo Mortis, will be released for Kindle and in paperback in September. I will be making a few promotional posts and sharing excerpts on my Patreon page. Other than that, I plan to continue travel and minimalism blog posts. I will also be accepting guest posts from other bloggers.

In addition, I’d like to start doing an “Author Spotlight” series. Perhaps once a month? Feel free to leave any suggestions or input in the comments below.

How Was Your July?

If you participated in July Camp NaNoWriMo 2018, how did it go for you? What did you learn from the experience? If you’re not a writer or didn’t participate, that’s OK! Please feel free to share your successes and stumbling blocks this month in the comments below!

Thanks for sticking with me!

-RB

Regina Bethory is a fiction author. She graduated from Christopher Newport University with a Bachelor’s in Directing and Play Writing and from Newport News Shipbuilding’s Apprentice School as a Test Electrician. She also has a degree in Funeral Services. As an avid minimalist and traveler, she enjoys spending her time learning new things, seeking new experiences and de-cluttering. When she is not writing, she can often be found in comic book stores and early morning matinees.

Dealing With a Day Job You Hate: Creating Castles from Carriers

Today I was sitting at my desk, staring out the window as rain pelted against it intermittently. Suddenly, a writing prompt came to mind! For almost seven years now I have held a day job in a place where I feel like a total outsider. Not only am I a female in a mostly male construction world but I’m also an artist in a world populated my engineers and others inclined towards mathematics. I held down a few others jobs before that, always knowing that this wasn’t the end result – that this wasn’t where I wanted to be.

Looking back at my childhood, I remember knowing even then that I was not meant for a typical 9-5 job. However, as time went on and I graduated from high school, I entered the work force to pay for clothes and college books, etc. One part of me wishes I had taken my writing more seriously back then but another part of me is glad that I waited for more life experience before sitting down to take part in the craft.

Using Creativity to Cope with the Day Job

Speaking with a friend at work about the rain that we’ve had on and off for the past two weeks (an unusually wet July), I mentioned, “I wonder if this is how people in England feel?” I’ve always wanted to visit England. I feel a strong pull towards both the location and the culture. It’s almost as though something inside of me is saying, “you belong over here!”

I went on to say, “I wouldn’t mind this weather so much if I had castles to stare at instead of carriers.” Outside of my office window I am greeted every day by a view of the USS Enterprise and the USS Gerald R. Ford. Constructed of rust and steel, my original thought was just how far from castles they really were. However, I began to think of how much they were similar to castles. And in some weird way this resulted in a means to cope.

Building Castles from Carriers

Though my job has become exponentially better since I first started working there, I often still feel imprisoned. Silly as it may sound, I started comparing my workplace to the “days-of-old.” This simple exercise in creativity might become a fun way to get through the tougher days.

After all, it isn’t a lie to say that I work inside of a gated fortress. The moat surrounding the fortress is represented by the druggies and criminals that peruse the area. We are constantly under attack by unseen forces (cyber-terrorism). And when you really look at them, how different are castles and carriers, really?

Letting the Imagination Roam

My new tactic for dealing with my day job is to pretend I’m really working for a fierce and righteous ruler. After all, both carriers and castles would have been built with blood, sweat and tears from the workers. I know I’ve given my fair share. They both take a long time to build and are constructed with the finest materials available. They both see battle, be under siege and be protected by legions of soldiers. I could go on, but I think you get the gist.

Sure. It sounds silly. But thinking I’m walking into a medieval adventure everyday is so much better than the soul-sucking alternative. Do you have a soul-sucking job? Or are you stuck in a day job where you feel you don’t belong? Feel stuck to a job because the pay is good? If you’ve got any fun and imaginative ideas on turning your day job into something fun, please share them below!

-RB

Regina Bethory is a fiction author. She graduated from Christopher Newport University with a Bachelor’s in Directing and Play Writing and from Newport News Shipbuilding’s Apprentice School as a Test Electrician. She also has a degree in Funeral Services. As an avid minimalist and traveler, she enjoys spending her time learning new things, seeking new experiences and de-cluttering. When she is not writing, she can often be found in comic book stores and early morning matinees.

9 Writing Prompts to Jump-Start Creativity

With the end of Camp NaNoWriMo in sight, some have already reached their monthly goals while others are still reaching for the finish line. Don’t fret! It’s not too late to get some more words in, even if it’s not on your original project. After all, one of the main points of the NaNoWriMo challenges is to get you to write everyday. With that being said, here are 9 writing prompts to carry you through this last weekend and hopefully the finish line.

9 Writing Prompts

  1. Local townsfolk see a witch fly over the moon on a broomstick…literally.
  2. A loved one is reincarnated as their widow’s (or widower’s) house plant. Tell a story from their POV.
  3. Start a new scene by finishing this dialogue: “If we get this money…”
  4. A woman who has been missing for three weeks suddenly reappears with no memory of where she has been for that time.
  5. “Trespassers will be prosecuted.” Local teens wander onto a “vacant” lot.
  6. A woman receives a fortune telling her to be more daring, “Fortune favors the brave.” She takes the advice to heart and shows kindness to a man who breaks into her home. What happens next?
  7. Tell a story from a house’s POV or even just the stories from one room.
  8. “When her head hit the floor, it bounced slightly then came to a halt as her eyes stared blankly ahead. She wasn’t supposed to die. Not like that.”
  9. A person stumbles across a tombstone with their name on it…and perhaps their birth year.

I hope that some of these (at least one) will benefit you and help get the creative cogs turning in your brain. Sometimes when I read  writing prompts, I have new ideas. Did any of these stand out to you? If so, which ones? Did they spark any creative fires? Let me know in the comments below.

Happy writing!

-RB

 

Regina Bethory is a fiction author. She graduated from Christopher Newport University with a Bachelor’s in Directing and Play Writing and from Newport News Shipbuilding’s Apprentice School as a Test Electrician. She also has a degree in Funeral Services. As an avid minimalist and traveler, she enjoys spending her time learning new things, seeking new experiences and de-cluttering. When she is not writing, she can often be found in comic book stores and early morning matinees.