FAST PLAYBACK IN MEDIA FILES WITH REDUCED IMPACT TO SPEECH QUALITY

• US 20180350388A1
• Filed: 05/31/2017
• Published: 12/06/2018
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jain, Deepa
• Granted Patent: US 10,629,223 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 21/043 by changing speed
• CPC Class Codes: G10L 21/055 for synchronising with other signals, e.g. video signals
• CPC Class Codes: G10L 21/057 for improving intelligibility
• CPC Class Codes: G11B 27/005 Reproducing at a different information rate from the information rate of recording for television signals H04N5/783
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel
• CPC Class Codes: H04N 5/783 Adaptations for reproducing at a rate different from the recording rate
• CPC Class Codes: H04N 9/8205 involving the multiplexing of an additional signal and the colour video signal

Abstract

The present invention is a system and method for increasing the playback speed of audio waves. The system analyzes an audio wave to detect a first silent section that has a length greater than a minimum short pause length required to distinguish between words. The system then calculates a new playback speed of the first silent section so that the total playback time for the first silent section is less than or equal to the minimum short pause length and controls an audio playback device to play the audio wave in a manner so that the first silent section is played back at the new playback speed. In another embodiment, the system analyzes spoken words, phonemes by phonemes, and increases the spoken word playback speed by dynamically reducing the length of each phoneme and inter-syllable silent pauses. Thus, the system functions equally well for all languages and accents.

Claims

1. A computer processing system for increasing the playback speed of audio files, comprising:

a computer processor having a non-transitory memory containing program code for;

analyzing an audio wave to detect a first silent section that has a length greater than a minimum short pause length required to distinguish between words;

calculating a new playback speed of the first silent section so that a total playback time for the first silent section is less than or equal to the minimum short pause length; and

controlling an audio playback device to play the audio wave in a manner so that the first silent section is played back at the new playback speed.

2. The system of claim 1, further comprising program code for detecting a second silent section after one or more first silent sections that has a length greater than a minimum long pause length required to distinguish between sentences.

3. The system of claim 2, further comprising program code for calculating a new playback speed of the second silent section so that a total playback time for the second silent section is equal to the minimum long pause length.

4. The system of claim 3, further comprising program code for adjusting an original playback speed of the second silent sections with respect to the first silent sections, such that the second silent sections are double the length of the first silent sections.

5. The system of claim 3, further comprising program code for playing back the audio wave with the second silent section at its new playback speed and the first silent section at its new playback speed.

6. The system of claim 4, further comprising program code for:

detecting video frames with fast content changes between the video frames in at least one of the first silent section and the section silent section; and

saving the video frames with an original playback speed.

7. A computer program product providing increased playback speed of audio files, the computer program comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions are readable by a computer to cause the computer to perform a method comprising the steps of:

analyzing an audio wave to detect a metadata flag representing one or more pauses in the audio wave;

calculating one or more new playback speeds of the pauses so that a total playback time for the pauses is less than or equal to a minimum pause length;

controlling an audio playback device to play the audio wave in a manner so that the pauses are played back at one of the new playback speeds based at least in part on the metadata flag.

8. The method of claim 7, further comprising the step providing user playback speed control when the metadata flag of the audio wave is conditional.

9. The method of claim 7, wherein the new playback speed is at least one of a recommended fast playback speed and a maximum fast playback speed.

10. The method of claim 9, wherein the recommended fast playback speed is calculated as an

Original Length/New Length, wherein New Length=Original File Length−

Σ

(short pause durations>

0.3 seconds−

0.3 seconds)−

Σ

(long pause durations>

1 second−

1 second)

11. The method of claim 9, wherein the maximum fast playback speed is calculated as

Original Length/New Length, wherein New Length=Original File Length−

Σ

(short pause durations−

0.1 seconds)−

Σ

(long pause duration−

0.5 seconds)

12. The method of claim 7, further comprising the step of detecting a short pause in the audio wave.

13. The method of claim 7, further comprising the step of detecting a long pause in the audio wave.

14. The method of claim 7, further comprising the step of playing back the audio wave at the new playback speed.

15. The method of claim 7, wherein the new playback speeds comprise spoken sections at an original speed and silent sections at a fast forwarded speed.

16. A method for increasing the playback speed of audio files, comprising the steps of:

analyzing an audio wave to detect one or more phonemes in a word in the audio wave;

analyzing each phoneme in the word to detect a low frequency repeating pattern section of the phoneme; and

calculating a new playback speed of the audio wave so that a total playback time for the low frequency repeating section is less than or equal to a minimum low frequency repeating section length; and

controlling an audio playback device to play the audio wave in a manner so that the low frequency repeating section is played back at the new playback speed.

17. The method of claim 16, further comprising the steps of:

analyzing each phoneme in the word to detect an inter-syllable silence section of the phoneme;

calculating a new playback speed of the audio wave so that a total playback time for the inter-syllable silence section is less than or equal to a minimum inter-syllable silence section length; and

controlling an audio playback device to play the audio wave in a manner so that the inter-syllable silence section is played back at the new playback speed.

18. The method of claim 17, wherein the low frequency repeating pattern section and the inter-syllable silence section are reduced by removing a portion of the low frequency repeating pattern section and a portion of the inter-syllable silence section.

19. The method of claim 17, wherein the low frequency repeating pattern section and the inter-syllable silence section are reduced by increasing the playback speed of a portion of the low frequency repeating pattern section and a portion of the inter-syllable silence section.

20. The method of claim 16, further comprising the steps of analyzing the audio wave to detect a first silent section that has a length greater than a minimum short pause length required to distinguish between words;

calculating a new playback speed of the first silent section so that a total playback time for the first silent section is less than or equal to the minimum short pause length; and

analyzing the audio wave to detect a second silent section after one or more first silent sections that has a length greater than a minimum long pause length required to distinguish between sentences;

calculating a new playback speed of the second silent section so that a total playback time for the second silent section is equal to the minimum long pause length; and

controlling the audio playback device to play the audio wave in a manner so that the first silent section and the second silent section are played back at the new playback speed.