“Empty the coins of your purse into your mind, and your mind will fill your purse with coins.” – Benjamin Franklin.
Sometimes the best results are achieved by connecting the right components together to create the best outcome. Case and point. While many firms today use both dictation and speech recognition technology very few of them have taken advantage of the synergy and fusion of them together.
If your firm hasn’t taken advantage of your attorneys dictating with “server-side speech recognition” or also known as “backend speech recognition” chances are you’re hemorrhaging both time and money and your time cannot be replaced. Once deployed firms can’t get over how easy it’s assimilated by the attorneys and support staff, however more importantly their flabbergasted by the return on investment which keeps going and going like the Energizer Bunny.
So, you may ask yourself how can I capitalize and cash in on this at my firm? Easy, there three software and hardware developers that already do this extremely well (BigHand, Olympus & Philips). These solutions are designed for large firms as enterprise premise-based applications like BigHand Enterprise and Philips SpeechExec Enterprise and smaller firms offered as BigHand Professional Cloud, Olympus Web SCP/ODMS and Philips SpeechExec Pro/SpeechLive Cloud. Attorneys can dictate into the systems through iOS and Android mobile devices, digital portable recorders and USB microphones such as the Olympus DS-9500/DS-9000 and RecMic II series RM-4110S/RM4010P, Philips DPM-8000/DPM-8100/DPM-6000 and SpeechMike series LFH3200/LFH3210/LFH3500/LFH3510/SMP3700/SMP3710/SMP4000/SMP4010.
After the dictation is converted to text both the audio and text are linked together and produce a karaoke like effect when the legal assistant plays the audio file hands-free with their foot pedal. Any mistakes that are made in recognition can be easily corrected which also improves the speech recognition engine accuracy and boosts the productivity of legal assistants. Below are some excerpts from a study commissioned by BigHand in 2017.
- It takes an assistants 2.3 times the length of a dictation to manually transcribe its contents
- It takes a legal assistants 1.5 times the length of a dictation to proof read its contents when returned from speech recognition
- Speech recognition allows assistants to convert dictations into finished content 36% more efficiently than manually typing
It was found that on average, attorney respondents create (or request) seven new documents per day. Without using BigHand Dictate, each document takes an average of 19 minutes to type manually. Creating the same document using BigHand Dictate reduces the time it takes by an average of 63% to only seven minutes. In total, it was found that BigHand Dictate saves attorneys an average of one hour and 24 minutes of typing time per day, which equates to 351 hours, or 50 full working days of additional time per user, per year.
Based on the average billable hour being charged at $425, and assuming conservatively that 25% of the attorney’s saved time will convert into billable hours, it’s assumed that BigHand Dictate can generate $37,400 of additional revenue per attorney, per year.
Graffen provides and supports all of these technologies so to learn more or find out what combination would have the best outcome for you give us a call or send us an email.