Which objective metrics (PESQ, STOI, DNSMOS, SI-SDR) and listening tests do the DeepFilterNet papers and the metric papers report, what do those numbers measure, and how far can they stand in for post-production acceptance of cleaned dialogue?
The DeepFilterNet papers report PESQ, CSIG, CBAK, COVL and STOI on Voicebank+Demand and, for DFN2, DNSMOS P.835 on the DNS4 blind set; neither the DFN2 nor the DFN3 paper (v1 HTML read) reports a listening test. DNSMOS P.835 is a non-intrusive predictor trained on crowd P.835 ratings of suppressor output, accurate per model (PCC 0.94-0.98) but weaker per clip (0.71-0.83). Intrusive metrics need a clean reference, which production dialogue lacks; SI-SDR ignores gain error. In URGENT 2024 two systems topped DNSMOS/NISQA yet scored low on MOS. No source read links any of these metrics to a post-production acceptance threshold.
The DeepFilterNet papers report PESQ, CSIG, CBAK, COVL and STOI on Voicebank+Demand and, for DFN2, DNSMOS P.835 on the DNS4 blind set; neither the DFN2 nor the DFN3 paper (v1 HTML read) reports a listening test. DNSMOS P.835 is a non-intrusive predictor trained on crowd P.835 ratings of suppressor output, accurate per model (PCC 0.94-0.98) but weaker per clip (0.71-0.83). Intrusive metrics need a clean reference, which production dialogue lacks; SI-SDR ignores gain error. In URGENT 2024 two systems topped DNSMOS/NISQA yet scored low on MOS. No source read links any of these metrics to a post-production acceptance threshold.
Curator qualifications: All 22 excerpts located; the absence of listening tests in DFN2/DFN3 v1 is a bounded negative over the HTML read. The DNSMOS model-level vs system-pool difference is kept as a non-contradiction.
Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
"citations": [
{
"url": "https://arxiv.org/abs/2305.08227v1",
"note": "candidate evidence excerpts"
},
{
"url": "https://arxiv.org/abs/2205.05474v1",
"note": "candidate evidence excerpts"
},
{
"url": "https://arxiv.org/abs/2110.01763v4",
"note": "candidate evidence excerpts"
},
{
"url": "https://arxiv.org/abs/1811.02508v1",
"note": "candidate evidence excerpts"
},
{
"url": "https://arxiv.org/abs/2506.01611v1",
"note": "candidate evidence excerpts"
}
]
}Evidence claims
- [sourced_fact] The DeepFilterNet papers report PESQ, CSIG, CBAK, COVL and STOI on Voicebank+Demand and, for DFN2, DNSMOS P.835 on the DNS4 blind set; neither the DFN2 nor the DFN3 paper (v1 HTML read) reports a listening test. DNSMOS P.835 is a non-intrusive predictor trained on crowd P.835 ratings of suppressor output, accurate per model (PCC 0.94-0.98) but weaker per clip (0.71-0.83). Intrusive metrics need a clean reference, which production dialogue lacks; SI-SDR ignores gain error. In URGENT 2024 two systems topped DNSMOS/NISQA yet scored low on MOS. No source read links any of these metrics to a post-production acceptance threshold. · locator: candidate evidence excerpts source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |