System and method for assessing audio files for transcription services
A system and method for assessing transcription costs based on an audio file are provided. The method includes method for assessing an audio file for transcription includes accessing at least one audio file for transcription assessment; analyzing the at least one audio file to determine at least one transcription characteristic based on the at least one audio file; and calculating, based on the at least one determined transcription characteristic, an initial bid value for transcription of the audio file.
1. A method for assessing an audio file for transcription, comprising:
generating signatures of voices determined to be unique within the audio file;
determining number of speakers captured within the audio file based on the signatures;
determining accent of each speaker from the speakers utilizing at least one of support vector machines using Gaussian mixture models (GMM-SVM), Gaussian mixture model with universal background model (GMM-UBM), and iVectors for speech processing applications;
identifying a main speaker and another speaker within the audio file;
identifying characteristics of noise in a recording of the main speaker, and characteristics of noise in a recording of the other speaker;
calculating a bid value for transcription of the audio file based on the number of speakers, the accent of each speaker, the characteristics of noise in the recording of the main speaker, and the characteristics of noise in the recording of the other speaker; and
identifying transcription candidates by a server to provide services based on matching of specific skillsets with the accent of each speaker.
2. The method of claim 1 , wherein the bid value depends on time of introducing the transcription of the audio file to a marketplace.
3. The method of claim 1 , wherein the bid value depends on current demand for transcriptions when introducing the transcription of the audio file to a marketplace.
4. The method of claim 1 , wherein the bid value depends on current availability of transcription services when introducing the transcription of the audio file to a marketplace.
5. A system for assessing an audio file for transcription, comprising:
a processing circuitry; and
a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
generate signatures of voices determined to be unique within the audio file;
determine number of speakers captured within the audio file based on the signatures;
determine accent of each speaker from the speakers utilizing at least one of support vector machines using Gaussian mixture models (GMM-SVM), Gaussian mixture model with universal background model (GMM-UBM), and iVectors for speech processing applications;
identify a main speaker and another speaker within the audio file;
identify characteristics of noise in a recording of the main speaker, and characteristics of noise in a recording of the other speaker;
calculate a bid value for transcription of the audio file based on the number of speakers, the accent of each speaker, the characteristics of noise in the recording of the main speaker, and the characteristics of noise in the recording of the other speaker; and
identify transcription candidates by a server to provide services based on matching of specific skillsets with the accent of each speaker.
6. The system of claim 5 , wherein the bid value depends on time of introducing the transcription of the audio file to a marketplace.
7. The system of claim 5 , wherein the bid value depends on current demand for transcriptions when introducing the transcription of the audio file to a marketplace.
8. The system of claim 5 , wherein the bid value depends on current availability of transcription services when introducing the transcription of the audio file to a marketplace.