~ Synchronizing Multimodal Recordings Using Audio-To-Audio Alignment - In Journal on Multimodal User Interfaces

The article titled “Synchronizing Multimodal Recordings Using Audio-To-Audio Alignment” by Joren Six and Marc Leman has been accepted for publication in the Journal on Multimodal User Interfaces. The article will be published later this year. It describes and tests a method to synchronize data-streams. Below you can find the abstract, pointers to the software under discussion and an author version of the article itself.

Synchronizing Multimodal Recordings Using Audio-To-Audio Alignment
An Application of Acoustic Fingerprinting to Facilitate Music Interaction Research

Abstract: Research on the interaction between movement and music often involves analysis of multi-track audio, video streams and sensor data. To facilitate such research a framework is presented here that allows synchronization of multimodal data. A low cost approach is proposed to synchronize streams by embedding ambient audio into each data-stream. This effectively reduces the synchronization problem to audio-to-audio alignment. As a part of the framework a robust, computationally efficient audio-to-audio alignment algorithm is presented for reliable synchronization of embedded audio streams of varying quality. The algorithm uses audio fingerprinting techniques to measure offsets. It also identifies drift and dropped samples, which makes it possible to find a synchronization solution under such circumstances as well. The framework is evaluated with synthetic signals and a case study, showing millisecond accurate synchronization.

To read the article, consult the author version of Synchronizing Multimodal Recordings Using Audio-To-Audio Alignment. The data-set used in the case study is available here. It contains a recording of balanceboard data, accelerometers, and two webcams that needs to be synchronized. The final publication is available at Springer via 10.1007/s12193-015-0196-1

The algorithm under discussion is included in Panako an audio fingerprinting system but is also available for download here. The SyncSink application has been packaged separately for ease of use.

To use the application start it with double click the downloaded SyncSink JAR-file. Subsequently add various audio or video files using drag and drop. If the same audio is found in the various media files a time-box plot appears, as in the screenshot below. To add corresponding data-files click one of the boxes on the timeline and choose a data file that is synchronized with the audio. The data-file should be a CSV-file. The separator should be ‘,’ and the first column should contain a time-stamp in fractional seconds. After pressing Sync a new CSV-file is created with the first column containing correctly shifted time stamps. If this is done for multiple files, a synchronized sensor-stream is created. Also, ffmpeg commands to synchronize the media files themselves are printed to the command line.

This work was supported by funding by a Methusalem grant from the Flemish Government, Belgium. Special thanks goes to Ivan Schepers for building the balance boards used in the case study. If you want to cite the article, use the following BiBTeX:

@article{six2015multimodal,
  author      = {Joren Six and Marc Leman},
  title       = {{Synchronizing Multimodal Recordings Using Audio-To-Audio Alignment}},
  issn        = {1783-7677},
  volume      = {9},
  number      = {3},
  pages       = {223-229},
  doi         = {10.1007/s12193-015-0196-1},
  journal     = {{Journal of Multimodal User Interfaces}}, 
  publisher   = {Springer Berlin Heidelberg},
  year        = 2015
}
  • The synchronized data from the two webcams, accelerometer and balanceboard in ELAN. From top to bottom the synchronized streams are two video-streams, balance-board data (red), accelerometer-data (green) and audio (black).

    The synchronized data from the two webcams, accelerometer and balanceboard in ELAN. From top to bottom the synchronized streams are two video-streams, balance-board data (red), accelerometer-data (green) and audio (black).

  • Conceptual drawing used as a basis for the SyncSync application. A reference stream (blue) can be synchronized with streams one and two. It allows a workflow where streams are started and stopped (red) or start before the reference stream (green).

    Conceptual drawing used as a basis for the SyncSync application. A reference stream (blue) can be synchronized with streams one and two. It allows a workflow where streams are started and stopped (red) or start before the reference stream (green).

  • A microcontroller fitted with an electret microphone and a microSD card slot. It can record audio in real-time together with sensor data.

    A microcontroller fitted with an electret microphone and a microSD card slot. It can record audio in real-time together with sensor data.

  • SyncSink Synchronize media files. A user-friendly interface to synchronize media and data files.  First a reference media-file is added using drag-and-drop. The audio steam of the reference is extracted and plotted on a timeline as the topmost box. Subsequently other media-files are added. The offsets with respect to the reference are calculated and plotted. CSV-files with timestamps and data recorded in sync with a stream can be attached to a respective audio stream. Finally, after pressing Sync!, the data and media files are modified to be exactly in sync with the reference.

    SyncSink Synchronize media files. A user-friendly interface to synchronize media and data files. First a reference media-file is added using drag-and-drop. The audio steam of the reference is extracted and plotted on a timeline as the topmost box. Subsequently other media-files are added. The offsets with respect to the reference are calculated and plotted. CSV-files with timestamps and data recorded in sync with a stream can be attached to a respective audio stream. Finally, after pressing Sync!, the data and media files are modified to be exactly in sync with the reference.

  • Multimodal recording system diagram. Each webcam has a microphone and is connected to the pc via USB. The dashed arrows represent analog signals. The balance board has four analog sensors but these are simplified to one connection in the schematic. The analog output of the microphones is also recorded through the DAQ. An analog accelerometer is connected with a microcontroller which also records audio.

    Multimodal recording system diagram. Each webcam has a microphone and is connected to the pc via USB. The dashed arrows represent analog signals. The balance board has four analog sensors but these are simplified to one connection in the schematic. The analog output of the microphones is also recorded through the DAQ. An analog accelerometer is connected with a microcontroller which also records audio.

  • Two streams of audio with fingerprints marked. Some fingerprints are present in both streams (green, O) while others are not (red, x). Matching fingerprints have the same offset, indicated by the dotted lines.

    Two streams of audio with fingerprints marked. Some fingerprints are present in both streams (green, O) while others are not (red, x). Matching fingerprints have the same offset, indicated by the dotted lines.

  • Synchronized streams in Sonic Visualizer. Here you can see two channel audio synchronized with accelerometer data (top, green) and balanceboard data (bottom, purple).

    Synchronized streams in Sonic Visualizer. Here you can see two channel audio synchronized with accelerometer data (top, green) and balanceboard data (bottom, purple).