• Week 42 (Extension)

    Additional summary statistics So, before I created a threshold I wanted to go through the resegmented audio files and get the snr values, so I can collect an average snr for each of the sub corpus and ages ranges. This will be one of my metrics for getting rid of...

  • Week 41 (Extension)

    Re-segmenting A few weeks ago we noticed a discrepancy with the number of hours I calculated in each of the CHILDES age ranges. According to the table below Rebekah calculated, the number of hours in each of the age ranges should be: 0-12: 16.99 hrs 13-24: 109.37 hrs 25-36: 91.22...

  • Week 40 (Extension)

    Voice activity detection There a lot of ways to do voice activity detection (VAD). In the time domain, VAD can be accomplished with short-time average energy, zero-crossings ratio, short-time average magnitude. In the frequency domain, one can achieve with spectral energy, long-term spectral envelope, Mel-frequency cepstral coefficients, and linear predictive...

  • Week 39 (Extension)

    Acoustic analysis pt. 2 This week I worked on comparing the mean power spectral density estimates (PSDs or mean LTASS) results of the three age ranges and the VoxForge corpus. The goal is to observe how the acoustics (spectrum) characteristics change across the ages and highlight any spectral patterns or...

  • Week 38 (Extension)

    Acoustic analysis pt. 1 Last week I finished resampling the three different age CHILDES age ranges: 0-12, 12-24, 24-36. This week I spent collecting the respective Power Spectrum Density Estimates (PSD) for each age range. For reference, here is a sketch of the process for collecting the PSD over each...

  • Week 37 (Extension)

    Resampling Finished I finished resampling the audio for the three age ranges. It took a lot longer than I expected. I ended up using the tic and toc functions in MATLAB to measure time: Resampling Time 0-12: 6.5 hrs Resampling Time 12-24: 9.5 hrs Resampling Time 24-36: 11.97 hrs CHILDES...

  • Week 36 (Extension)

    The Return of LTASS For a recap, I’m still estimating the Long Term Average Speech Spectrum (LTASS) and other associated frequency characteristics for the CHILDES corpus. Resampling In order to properly calculate LTASS it is necessary that all the audio files in CHILDES corpus have the same sampling frequency. Namely,...

  • Week 35

    Non-verbal communication This week was finals week, so it was difficult to think about my project. Though, one of my finals was a presentation for my human robot-interaction class. So, ideas about computers doing things at a human level or alongside humans was definitely on my mind (of course, it’s...