出自Full Circle 中文项目主页
The skill of speech and also the art of transcription are blended to create a new state-of-the-art technology called as the automated speech recognition software. The ASR or even the automatic speech recognition software programs are found to be the talk of the town. Speech recognition is a dream for all of us from the traditional times of star wars and other science fiction movies and stories. Have our dreams become a reality?? Today, it's been partially fulfilled using the new arrivals within the markets. Each company has been into this competition of giving the very best speech recognition software around the world market. What is happening towards the race among themselves? It jogs my memory from the hare and also the tortoise story. The slow and steady appears like it's won the race, but yet has miles to touch the finish line. Discussing by what exactly may be the goal of the race?? Is it either dealing with the very best or getting to the people, is again a million dollar question. With the revenues pooled in for speech recognition have learned to drain, there is a have to analyze the development with time factor, that will clearly show a flattened graph showing the stagnant nature of the software research and development.
Imagine a situation, in which you have invested on speech recognition software for many thousand dollars per month and find it to be unworthy since they type in your dictations wrongly, test is replaced and jumbled, and also the context becomes different, what a chaos that would create. The frustration that's exhibited at those times is actually unbearable. Flawless products or services are nowhere found since everything on the planet comes with unique pros and cons. This is applicable to the speech-to-text software too. It's its very own flaws and demerits, which limits the usage of it inside the small community. The idea needs more attention and research to achieve in order to compete with the languages which have been developed over millions of years.
The ethnologue of the world seems to be far too long and unending. The languages that people speak today are the growth and development of it over millions of years along with all the efforts of countless generations. All animals contact each other, but it is only the humans who have formulated the communication in predefined set of signals known as the language. The Cortical Speech Center is again an evolutionary feature that only the humans posses, which differentiates the human brain from the other animals within the animal kingdom. Hence, the speech recognition softwares which has a very recent history compared to the languages has to travel not millions but at least few decades to know minimal about the speech and languages spoken by different categories of people.
The drawbacks from the voice recognition or audio-to-text software are:
It cannot understand all the words after working hours together training the software. Time is precious in the end we have only 24 hours a day!!! All the punctuations such as coma, full stop, semicolon, hyphenation requires the speaker to dictate wherever he/she wants one. Understanding the context is another major drawback or demerit: Some words especially in English have many meanings and requires for use in the correct context to obtain great results in the records. The software does not appear to understand the context in many of the places. Homophones are again a hard task to deal with for that audio to text software: Different words with the same pronunciation but different meanings: For example elicit-illicit; desert-dessert; there-their; flour-flower; bowel-bowl; words with same pronunciation but different spelling and meaning, that are utilized in different context, confuse the software leading to bloopers and hilarious phrases and sentences. The other major black mark concerning the speech recognition is that it cannot comprehend the varied types ofaccent that is contained in one single language. Understanding the words inside a neutral slang is difficult for the program then just how can it ever understand the different slangs or accents used by differing people all over the world!!
In 1997, Bill gates gave a open statement that "In this 10-year time frame, In my opinion that we'll not only be using the laptop keyboard and also the mouse to have interaction, but during that time we will have perfected speech recognition and speech output well enough those will become a standard area of the interface." Now, it's Three years past a decade and yet speech recognition is only in the primitive stage of usage and development.
Hence, to conclude transcription industry includes a bigger give the audio-to-text software. Transcriptionists are not obsolete. They've their own space and want in the field for his or her integrity, caliber, and experience of the.