How to increase accuracy in Speech Recognition

How to improve accuracy with Dragon NaturallySpeaking Recorder Edition

Answer ID 5762   |    Published 06/09/2009 12:00 AM   |    Updated 04/16/2010 04:34 PM
How to improve accuracy with Dragon NaturallySpeaking Recorder Edition Information:
There are multiple ways to improve accuracy when using Dragon NaturallySpeaking Recorder Edition:
  • Running the Acoustic and Language Model Optimizer.
  • Performing corrections.
  • Analyzing e-mail.

Method 1: Performing corrections
After the user transcribes an audio file, the user should correct any words that were not recognized properly. With the Recorder Edition, it is not possible to correct words by voice.
To perform corrections:
  1. Open a digital recorder user profile.
  2. Perform a transcription of an audio file by using the "Transcribe" button on the DragonBar.
  3. Using the mouse, highlight the text that needs to be corrected.
  4. Click the "Correction" button on the DragonBar or press the Correction Hotkey (the "minus" key on the numberic keypad, by default) to display the Correction dialog.
  5. If the correct word is displayed in the Correction dialog, select that word to make the correction.
    Note: The user can click the "Playback" button at this time to verify what was originally dictated.
  6. If the correct word is not displayed in the Correction dialog, click the “Spell That…” option and type out the correct word in the Spell dialog.
  7. Press the "Enter" key or click “OK” to make the correction.
  8. Correcting in this manner will adapt the user's voice files, leading to continuously improving accuracy.
Method 2: Analyzing e-mail
Use the Increase Accuracy from E-mail tool to add the names of people the user has sent e-mail to into the Dragon vocabulary. The user has the option to edit these names and can also have Dragon scan the contents of the user's sent e-mail and add it to the language model.
To analyze e-mail:
  1. Open a digital recorder user profile.
  2. Click "Tools > Accuracy Center".
  3. Click the "Increase accuracy from e-mail" link.
  4. The Increase Accuracy from E-mail wizard opens. Click the "Next" button.
  5. Select the e-mail source to be used:
    • Lotus Notes
    • Microsoft Outlook
    • Outlook Express
  6. Select one or both of the following options:
    • Add contact names from e-mail to the vocabulary
    • Improve my speech files from my e-mail writing style
  7. Select one of the following options:
    • Consider e-mail written since my last scan
    • Consider all e-mail
  8. Click the "Next" button to start analyzing e-mail.
Method 3: The Acoustic and Language Model Optimizer
Before running the Acoustic and Language Model Optimizer, make sure the "Store corrections in archive" option is enabled under "Tools > Options > Data tab". If this option is not enabled, the user may see a message that there is not enough data for the Acoustic and Language Model Optimizer to process.
To run the Acoustic and Language Model Optimizer:
  1. Open a digital recorder user profile.
  2. Click "Tools > Accuracy Center".
  3. Click the "Run the Acoustic and Language Model Optimizer" link.
  4. Enable the "Perform Acoustic Optimization" and/or the "Perform Language Model Optimization" options.
    Notes:
    • Select "Perform Acoustic Optimization" to update the user profile with accumulated acoustic data from any corrections made by the user.
    • Select "Perform Language Model Optimization" to update the language model. The language model contains statistical information that predicts which words are most likely to occur in the context of the user’s speech.
  5. Click the "Go" button to begin the optimization.
  6. The Acoustic and Language Model Optimizer dialog box will display the amount of time to finish adapting the user files and display a progress bar to indicate how much of the job is complete. It generally takes as long to adapt the user files as the amount of data stored. For example, if there is 30 minutes of acoustic data stored, the processing time will be approximately 30 minutes.
  7. Once the optimization has completed, save the user profile by clicking "NaturallySpeaking > Save User Files".
General tips on increasing accuracy:

  • If using the digital recording device's built-in microphone, always hold the device at the same distance from the user's mouth. Some users rest the device on their jaw for the most consistent results.
  • Consider connecting a headset microphone to the digital recording device rather than using the built-in microphone. Using a high-quality external microphone is likely to produce better quality recordings.
  • Adjust the Speed vs. Accuracy setting under "Tools > Options > Miscellaneous tab". The Speed vs. Accuracy setting adjusts the number of words and phrases that the program examines in order to find a word match. The more words that are examined, the greater the possibility of an accurate match. However, this comes at the expense of using more memory and taking a longer time to recognize the user's speech. The user can adjust the Speed vs. Accuracy slider to influence the performance of Dragon. As a general rule, the user should move the slider farther to the right on faster machines than on slower ones.

Transcription Overview

Overview

Whether you need to transcribe highly sensitive audio information to text or turn a podcast into a typed transcription that can be found through Internet search engines, transcription services promptly provide quality transcriptions of client's audio to text. Transcription services have been around for years, and have helped numerous companies, individuals, and government agencies transcribe spoken words into typed or written content for legal or practical reasons.
A transcription is a written or printed representation of something. When conducting an important meeting or conversation, it is practical to have a hard copy of spoken words for reference later. If a person were to transcribe the audio recorded from the meeting his or herself, he or she would have a tedious time organizing all the information, especially if it was a particularly long meeting or conversation. As we know, time is money, and that's where transcription services come in. Using the latest technology and professional experience, Speechpad accurately transcribes recorded audio to text so that you won't have to.
Transcription services make sure that clients have quality and accurate transcriptions of audio to text so that the text can be easily organized and archived for later reference. This is highly important for companies and individuals that want to stay organized and have hardcopies of conversations to protect them from liability. Businesses can take advantage of transcription services by recording meetings, phone calls, radio broadcasts, and television shows. This serves as a much easier way to take review notes than through listening to potentially hours of audio.
Transcription services can especially help insurance companies through the use of insurance transcriptions. Insurance companies record conversations from accident victims that can be used as reference later. These conversations are later transcribed verbatim to catch every word, pause, and speech fragment. Transcription services make it much easier for insurance companies to search through documents rather than sit through hours and hours of audio.
The key factor in transcriptions is accuracy. Without an accurate transcription from audio to text, key words, phrases or meanings could be lost in translation. A good transcription service will assure you that your transcription will be handled with the utmost accuracy; if you are dissatisfied for any reason, we offer a full refund.
The second major factor when it comes to transcriptions is the time it takes for a service to transcribe your audio. Some smaller shops can't handle peak loads and will return your transcription late, or quality will suffer. A quality transcription service guarantees turn around time so you can rest assured you will have the transcript when you expect it.
By offering a variety of services, Speechpad can service your every transcription need regardless of file format, from insurance transcription, podcast transcription, voice to text, audio to text, mp3 to text, and even video transcription. We serve everyone from the Fortune 1000 to the college student recording his podcast from his dorm room.