Numbers stress: dropouts
A 5 second excerpt of this group's take, dropouts. Short spans silenced outright, as a packet-switched call drops them, so a transcriber must decide between a pause and a missing word. Delivered as flac at 24000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
Specifications
- Utterance
- numbers-stress
- Voice
- am_liam
- Speech Rate
- 1
- Synthetic
- true
- Disclosure
- Synthetic speech. Generated locally with a text-to-speech model from an authored script; not a recording of a real person, and no real customer, order or incident is described.
- Schema Version
- 1
- Sample Rate
- 24000
- Channels
- 1
- Codec
- flac
- Duration Seconds
- 5
- Role
- ladder-variant
- Variant
- dropouts
- Degradation
- dropouts
- Param Spans
- [[1.0, 0.12], [3.2, 0.25]]
Testing contract
Expected to pass- Scenario
- Decode this variant and the clean plate in the same group, then measure the difference against the parameters recorded in its specs.
- Expected result
- It decodes to the same duration as the plate and differs from it by exactly what was applied: codec flac, sampleRate 24000. The degradation was APPLIED rather than estimated, so the figure in the specs is the true answer and not a second measurement of it.
What is a .flac file?
FLAC (Free Lossless Audio Codec) compresses PCM audio losslessly, typically to about half the size of the original with no quality loss. It supports metadata tags, embedded cover art, and fast seeking. It is favored for archival and audiophile music libraries.
How to use this file
Use an example FLAC to test lossless decoding, verify bit-exact round-trips against source PCM, and exercise tag parsing and transcoding to lossy formats.
How to use this file for testing
“Numbers stress: dropouts” is a deterministic Novus Examples fixture for ASR testing, Audio analysis, Media pipeline testing. Short synthetic digit/tone utterances with transcript JSON and clean↔noise pairs, for testing ASR loaders, WER harnesses, and audio preprocessing.
Documented properties for this file: ladder-variant · 24000 Hz · 1 ch. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.
Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such, expect parsers to fail loudly rather than silently accept them.
Media fixtures are short and synthetic by design. Prefer waveform or transcript ground truth in the same group when measuring ASR, trim, upscale, or sync tools; do not assume broadcast-quality masters.
Run ASR on the clip and score the transcript against the documented ground-truth script; clips are short, synthetic, and read from a fixed word or digit sequence.
Code examples
<audio controls preload="none" src="dropouts.flac"></audio>Related files
- wavComplaint call: chain telephoneA 5 second excerpt of this group's take, telephone chain. Band-limited, resampled and companded in one pass: the whole telephone path applied at once rather than one effect at a time. Delivered as pcm_mulaw at 8000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
- flacComplaint call: clippedA 5 second excerpt of this group's take, clipping. Samples driven past a fixed threshold and flattened, the damage a hot microphone does and the one no codec can undo. Delivered as flac at 24000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
- wavComplaint call: codec g722 16kA 5 second excerpt of this group's take, codec. Encoded and decoded through a real speech codec, so the artefacts are the ones the format actually produces rather than a simulation of them. Delivered as adpcm_g722 at 16000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
- gsmComplaint call: codec gsm 8kA 5 second excerpt of this group's take, codec. Encoded and decoded through a real speech codec, so the artefacts are the ones the format actually produces rather than a simulation of them. Delivered as gsm at 8000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
- mp3Complaint call: codec mp3 128A 5 second excerpt of this group's take, codec. Encoded and decoded through a real speech codec, so the artefacts are the ones the format actually produces rather than a simulation of them. Delivered as mp3 at 24000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
- mp3Complaint call: codec mp3 32A 5 second excerpt of this group's take, codec. Encoded and decoded through a real speech codec, so the artefacts are the ones the format actually produces rather than a simulation of them. Delivered as mp3 at 24000 Hz mono. Scored against plate.flac in the same group, which is the same five seconds undamaged. The parameters in the specification are what the file MEASURED, not what was requested of it.
Generated by generation/audio_ladder_wave.py. Free for any use, no attribution required, license.