Add speech-to-reverberation modulation energy ratio (SRMR) metric #1792
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
| @@ -6,3 +6,4 @@ mir-eval >=0.6, <=0.7 | |||
| speechmetrics @ git+https://github.com/aliutkus/speechmetrics | |||
| fast-bss-eval >=0.1.0, <0.1.5 | |||
| torch_complex <=0.4.3 # needed for fast-bss-eval | |||
| srmrpy @ git+https://github.com/jfsantos/SRMRpy | |||
There was a problem hiding this comment.
note this wont be installed with pypi
There was a problem hiding this comment.
Turned out this repo is not tested, so we shall not rely with parity on their numbers
ref: jfsantos/SRMRpy#15
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
|
for the record of detly/gammatone#16 (comment) |
|
@SkafteNicki @quancs have you checked the testing of the added package? |
I tested just now. but the tests didn't get passed. |
|
@quancs lets add a note that this metric is experimental as we do not have any parity or own reference values to test with |
OK. |
What does this PR do?
Add SRMR metric
Before submitting
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃
📚 Documentation preview 📚: https://torchmetrics--1792.org.readthedocs.build/en/1792/