List your company

Speech Coding on Emilia clean subset (test)

3.646DNSMOSRFSQ-4S-NU-LN
2.648642.907573.16653.42543Aug 20, 2025

Evaluation results

MethodLinks
RFSQ-4S-NU-LNBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=4, Bit Allocation=Non-Uniform (8, 6, 5, 5), Conditioning Strategy=LayerNorm2025.083.6463.8
RFSQ-4S-Uni-LNBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=4, Bit Allocation=Uniform, Conditioning Strategy=LayerNorm2025.083.5983.83
RVQ-4×64Bitrate=1.8 kbps, Sampling Rate=24 kHz, Stages=4, Quantization Architecture=RVQ, Codebook size=642025.083.5183.81
RFSQ-4S-NU-ScaleBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=4, Bit Allocation=Non-Uniform, Conditioning Strategy=Scale2025.083.4213.7
RFSQ-8S-Uni-LNBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=8, Bit Allocation=Uniform, Conditioning Strategy=LayerNorm2025.083.3563.65
RFSQ-2S-NU-LNBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=2, Bit Allocation=Non-Uniform, Conditioning Strategy=LayerNorm2025.083.2893.62
RFSQ-4S-NU-NoBitrate=1.8 kbps, Sampling Rate=24 kHz, Number of Stages=4, Bit Allocation=Non-Uniform, Conditioning Strategy=none2025.083.1873.58
FSQ-4D-UniformBitrate=1.8 kbps, Sampling Rate=24 kHz, Quantization Architecture=Single-stage FSQ, Bit Allocation=Uniform2025.082.9653.51
LFQ-24DBitrate=1.8 kbps, Sampling Rate=24 kHz, Quantization Architecture=Lookup-Free Quantization2025.082.8143.52
VQ-EMA-4×64-PQBitrate=1.8 kbps, Sampling Rate=24 kHz, Stages=4, Quantization Architecture=VQ-EMA, Type=Product Quantization2025.082.6873.42