Audio file quality and accuracy assessment
Disclosed computer-based systems and methods for analyzing a plurality of audio files corresponding to text-based news stories and received from a plurality of audio file creators are configured to (i) compare quality and/or accuracy metrics of individual audio files against corresponding quality and/or accuracy thresholds, and (ii) based on the comparison: (a) accept audio files meeting the quality and/or accuracy thresholds for distribution to a plurality of subscribers for playback, (b) reject audio files failing to meet one or more certain quality and/or accuracy thresholds, (c) remediate audio files failing to meet certain quality thresholds, and (d) designate for human review, audio files failing to meet one or more certain quality and/or accuracy thresholds by a predetermined margin.
1. A method performed by a computing system, the method comprising:
making a first determination that an average volume of an audio file is (i) less than a minimum volume threshold or (ii) greater than a maximum volume threshold;
in response to making the first determination, making a second determination that the audio file cannot be remediated by the computing system;
in response to making the second determination, making a third determination of whether the audio file is so flawed as to require rejection;
in response to making the third determination, designating the audio file for review by a human or rejecting the audio file;
calculating an audio pace of the audio file by dividing a number of words of a reference file that corresponds to the audio file by a duration of the audio file; and
determining that the audio pace is (i) greater than a maximum audio pace threshold or (ii) less than a minimum audio pace threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the audio pace is (i) greater than the maximum audio pace threshold or (ii) less than the minimum audio pace threshold.
2. The method of claim 1 , further comprising:
generating a text file from the audio file; and
determining that a number of words in the text file matching words in the reference file is less than a word match threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the number of words in the text file matching words in the reference file is less than the word match threshold.
3. The method of claim 1 , further comprising:
determining a first number of words in the reference file;
determining a duration of the audio file;
estimating a second number of words in the audio file based on the duration and an estimated words-per-minute rate of the audio file; and
determining that a difference between the first number of words and the second number of words is greater than a word count threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first number of words and the second number of words is greater than the word count threshold.
4. The method of claim 1 , further comprising:
determining a first number of sentences in the reference file that corresponds to the audio file;
determining a second number of sentences in the audio file; and
determining that a difference between the first number of sentences and the second number of sentences is greater than a sentence count threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first number of sentences and the second number of sentences is greater than the sentence count threshold.
5. The method of claim 1 , further comprising:
estimating a first duration of the audio file based on a number of words in the reference file;
determining an actual second duration of the audio file; and
determining that a difference between the first duration and the actual second duration is greater than a duration threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first duration and the actual second duration is greater than the duration threshold.
6. The method of claim 1 , further comprising:
determining that background noise in the audio file is greater than a background noise threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that background noise in the audio file is greater than the background noise threshold.
7. The method of claim 6 , further comprising:
in response to determining that background noise in the audio file is greater than the background noise threshold, generating a noise-reduced version of the audio file by applying one or more noise reduction algorithms to the audio file; and
determining that background noise in the noise-reduced version of the audio file is greater than the background noise threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that background noise in the noise-reduced version of the audio file is greater than the background noise threshold.
8. The method of claim 1 , further comprising:
generating a compressed audio file by compressing a dynamic range of the audio file in response to making the first determination; and
determining that a second average volume of the compressed audio file is (i) greater than the maximum volume threshold or (ii) less than the minimum volume threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the second average volume of the compressed audio file is (i) greater than the maximum volume threshold or (ii) less than the minimum volume threshold.
9. The method of claim 1 , further comprises:
determining that a peak volume of the audio file is greater than a peak volume threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the peak volume of the audio file is greater than the peak volume threshold.
10. The method of claim 1 , wherein rejecting the audio file comprises transmitting an indication to an audio file creator associated with the audio file, the indication comprising one or more of: (i) a notification that the audio file has been rejected, (ii) at least one reason for rejecting the audio file, and (iii) a request that the audio file creator resend a corrected version of the audio file.
11. A computing system comprising:
one or more processors; and
a non-transitory computer-readable memory storing instructions that, when executed by the one or more processors, cause the computing system to perform functions comprising:
making a first determination that an average volume of an audio file is (i) less than a minimum volume threshold or (ii) greater than a maximum volume threshold;
in response to making the first determination, making a second determination that the audio file cannot be remediated by the computing system;
in response to making the second determination, making a third determination of whether the audio file is so flawed as to require rejection;
in response to making the third determination, designating the audio file for review by a human or rejecting the audio file;
calculating an audio pace of the audio file by dividing a number of words of a reference file that corresponds to the audio file by a duration of the audio file; and
determining that the audio pace is (i) greater than a maximum audio pace threshold or (ii) less than a minimum audio pace threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the audio pace is (i) greater than the maximum audio pace threshold or (ii) less than the minimum audio pace threshold.
12. The computing system of claim 11 , the functions further comprising:
generating a text file from the audio file; and
determining that a number of words in the text file matching words in the reference file is less than a word match threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the number of words in the text file matching words in the reference file is less than the word match threshold.
13. The computing system of claim 11 , the functions further comprising:
determining a first number of words in the reference file;
determining a duration of the audio file;
estimating a second number of words in the audio file based on the duration and an estimated words-per-minute rate of the audio file; and
determining that a difference between the first number of words and the second number of words is greater than a word count threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first number of words and the second number of words is greater than the word count threshold.
14. The computing system of claim 11 , the functions further comprising:
determining a first number of sentences in the reference file that corresponds to the audio file;
determining a second number of sentences in the audio file; and
determining that a difference between the first number of sentences and the second number of sentences is greater than a sentence count threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first number of sentences and the second number of sentences is greater than the sentence count threshold.
15. The computing system of claim 11 , the functions further comprising:
estimating a first duration of the audio file based on a number of words in the reference file;
determining an actual second duration of the audio file; and
determining that a difference between the first duration and the actual second duration is greater than a duration threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first duration and the actual second duration is greater than the duration threshold.
16. The computing system of claim 11 , the functions further comprising:
determining that background noise in the audio file is greater than a background noise threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that background noise in the audio file is greater than the background noise threshold.
17. The computing system of claim 16 , the functions further comprising:
in response to determining that background noise in the audio file is greater than the background noise threshold, generating a noise-reduced version of the audio file by applying one or more noise reduction algorithms to the audio file; and
determining that background noise in the noise-reduced version of the audio file is greater than the background noise threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that background noise in the noise-reduced version of the audio file is greater than the background noise threshold.
18. A non-transitory computer readable memory storing instructions that, when executed by a computing system, cause the computing system to perform functions comprising:
making a first determination that an average volume of an audio file is (i) less than a minimum volume threshold or (ii) greater than a maximum volume threshold;
in response to making the first determination, making a second determination that the audio file cannot be remediated by the computing system;
in response to making the second determination, making a third determination of whether the audio file is so flawed as to require rejection;
in response to making the third determination, designating the audio file for review by a human or rejecting the audio file;
calculating an audio pace of the audio file by dividing a number of words of a reference file that corresponds to the audio file by a duration of the audio file; and
determining that the audio pace is (i) greater than a maximum audio pace threshold or (ii) less than a minimum audio pace threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the audio pace is (i) greater than the maximum audio pace threshold or (ii) less than the minimum audio pace threshold.
19. The non-transitory computer readable memory of claim 18 , the functions further comprising:
generating a text file from the audio file; and
determining that a number of words in the text file matching words in the reference file is less than a word match threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the number of words in the text file matching words in the reference file is less than the word match threshold.
20. The non-transitory computer readable memory of claim 18 , the functions further comprising:
determining a first number of words in the reference file;
determining a duration of the audio file;
estimating a second number of words in the audio file based on the duration and an estimated words-per-minute rate of the audio file; and
determining that a difference between the first number of words and the second number of words is greater than a word count threshold,
wherein making the second determination comprises making the second determination additionally in response to determining that the difference between the first number of words and the second number of words is greater than the word count threshold.