Deaf and Hard-of-Hearing Perspectives on Imperfect Automatic Speech Recognition for Captioning One-on-One Meetings

This webpage contains supplemental online information for the following ASSETS 2017 paper:

Larwan Berke, Christopher Caulfield, Matt Huenerfauth. 2017. Deaf and Hard-of-Hearing Perspectives on Imperfect Automatic Speech Recognition for Captioning One-on-One Meetings. In Proceedings of the The 19th International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS '17). ACM, New York, NY, USA.

Technical Specifications of Videos

The video files linked below are MKV files (with embedded captions). These files can be played using VLC Media Player. The files have following technical specifications:

• Kind: MKV Movie File
• UTI: org.perian.matroska
• Container
• Format: Matroska
• Format version: Version 4 / Version 2
• Video
• ID: 1
• Format: AVC
• Format/Info: Advanced Video Codec
• Format profile: High@L5.1
• Format settings, CABAC: Yes
• Format settings, ReFrames: 16 frames
• Codec ID: V_MPEG4/ISO/AVC
• Width: 1 920 pixels
• Height: 1 080 pixels
• Pixel aspect ratio: 1.000
• Display aspect ratio: 16:9
• Frame rate mode: Constant
• Frame rate: 29.970 (30000/1001) FPS
• Color space: YUV
• Chroma subsampling: 4:2:0
• Bit depth: 8 bits
• Scan type: Progressive
• Writing library: x264 core 148 r236 a01e339
• Encoding settings: cabac=1 / ref=16 / deblock=1:0:0 / analyse=0x3:0x133 / me=umh / subme=10 / psy=1 / psy_rd=1.00:0.00 / mixed_ref=1 / me_range=24 / chroma_me=1 / trellis=2 / 8x8dct=1 / cqm=0 / deadzone=21,11 / fast_pskip=1 / chroma_qp_offset=-2 / threads=12 / lookahead_threads=2 / sliced_threads=0 / nr=0 / decimate=1 / interlaced=0 / bluray_compat=0 / constrained_intra=0 / bframes=8 / b_pyramid=2 / b_adapt=2 / b_bias=0 / direct=3 / weightb=1 / open_gop=0 / weightp=2 / keyint=250 / keyint_min=25 / scenecut=40 / intra_refresh=0 / rc_lookahead=60 / rc=crf / mbtree=1 / crf=23.0 / qcomp=0.60 / qpmin=0 / qpmax=69 / qpstep=4 / ip_ratio=1.40 / aq=1:1.00
• Audio
• ID: 2
• Format: PCM
• Format settings, Endianness: Big
• Codec ID: A_PCM/INT/BIG
• Bit rate mode: Constant
• Channel(s): 2 channels
• Sampling rate: 48.0 kHz
• Bit depth: 16 bits

Mock Meeting Scenario Videos

The following twelve video files (MKV) were used to generate stimuli for the studies.

• Meeting-01
• Meeting-02
• Meeting-03
• Meeting-04
• Meeting-05
• Meeting-06
• Meeting-07
• Meeting-08
• Meeting-09
• Meeting-10
• Meeting-11
• Meeting-12

Example Stimuli from Pilot Study

The following twelve video files contain examples of stimuli from this study, showing each markup type.

• Pilot-01, Markup Type: No Change
• Pilot-02, Markup Type: Bold on Confident
• Pilot-03, Markup Type: Bold on Uncertain
• Pilot-04, Markup Type: Green on Confident
• Pilot-05, Markup Type: Red on Uncertain
• Pilot-06, Markup Type: Small font size on Uncertain
• Pilot-07, Markup Type: Levels of gray color based on confidence
• Pilot-08, Markup Type: Levels of font size based on confidence
• Pilot-09, Markup Type: Empty underline on Uncertain
• Pilot-10, Markup Type: Italics on Uncertain
• Pilot-11, Markup Type: Underline on Uncertain
• Pilot-12, Markup Type: Underline and gray color on Uncertain

Example Stimuli from Larger Study

The following four video files contain examples of stimuli from this study, showing each markup type. Participants in the study actually saw twelve videos, three of each type.

• Larger-01, Markup Type: No Change
• Larger-01, Markup Type: Yellow
• Larger-01, Markup Type: Italics
• Larger-01, Markup Type: Underline

Survey Questions from Larger Study

The following files are comma-separated-values (CSV) files containing the English text version and answer-choice options for each survey question, along with the comprehension questions and answer choices from the study.

• Larger-Pre-Demographics, CSV file containing pre-experiment demographic question text
• Larger-Post-Questions, CSV file containing post-experiment question text
• Larger-Comprehension, CSV file containing comprehension questions