Kaldi fbank lifter coefficient behavior across versions

Context

Kaldi's compute-fbank-feats added the --lifter flag to apply HTK-style liftering to filterbank coefficients. Earlier releases computed raw filterbank energies without this option, while current releases default to a lifter coefficient of 22 when the flag is present.

Unresolved behavior

Acoustic models trained on features extracted with different lifter settings (or without liftering) can exhibit mismatched input distributions. The documentation does not specify whether a model trained on liftered features expects the same coefficient at inference time, or whether omitting --lifter entirely is equivalent to a coefficient of zero.

Constraints

• Model checkpoints lack metadata recording the lifter coefficient used during training.
• Re-extracting features for a large corpus with varying --lifter values is computationally expensive.
• Downstream components (e.g., CMVN stats, i-vector extractors) assume a fixed feature dimension but not a fixed spectral tilt.

Questions

1. Does the --lifter coefficient need to match exactly between training and decoding, or is the effect limited to a linear scaling that CMVN absorbs?
2. When --lifter is omitted, does Kaldi apply a coefficient of zero or retain a previous default?
3. Is there a recommended practice for recording the lifter setting alongside model artifacts to avoid silent mismatch?