- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes Dynamic Band Splitting (DBS), an architecture modification for band-split audio source separation models (such as BSRNN, TIGER, BS-RoFormer, and Mel-Band RoFormer) that predicts input-conditioned frequency band boundaries within four fixed frequency blocks under a fixed band-token budget, followed by token smoothing, frequency refinement, and mask decoding.
Critical strengths
The paper is well written and clear, and adapting frequency band boundaries based on the spectral structure of the input mixture is an intuitive engineering modification for band-split architectures.
Critical weaknesses
-
There is no significant methodological novelty here for an ICLR publication beyond a straightforward architectural modification that trades off memory and more than 50% extra compute (FLOPs/MACs) for marginal SI-SDR gains over existing band-split models like BSRNN and TIGER. For example, in Table 1, going from BSRNN to DBS-BSRNN gives only about a 1.4 dB improvement (7.7 to 9.1 dB) while increasing compute from 76.6 to 124.0 G/s MACs (more than a 60% increase in FLOPs), and similar compute increases hold across the other tables for 0.3 to 1.4 dB gains. Furthermore, reporting a second decimal point in all SNR/SDR tables shows a disconnect from what constitutes a statistically or perceptually significant difference between models in the 7 to 10 dB regime, where even a 1 dB difference is difficult to distinguish.
-
The choice and implementation of the learnable filterbank baseline in Table 3 (which collapses to dB SI-SDR) is questionable; if the authors' baseline setup did not work, including a broken baseline in the main table is not informative. Prior work such as Conv-TasNet [A] and two-step sound separation on learned latent targets [B] has already shown that learnable filterbanks and source-structured latent spaces work well for separation, so learning source-adapted spectral or latent structure is not a new finding.
[A] Luo, Y. and Mesgarani, N., 2019. Conv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(8), pp. 1256-1266.
[B] Tzinis, E., Venkataramani, S., Wang, Z., Subakan, C. and Smaragdis, P., 2020, May. Two-step sound source separation: Training on learned latent targets. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 31-35). IEEE.
Questions for authors
How do the static baselines (such as BSRNN and TIGER) perform when scaled up to match the exact same FLOPs/MACs budget (e.g., 124 G/s MACs on DnR v2) and extra refinement layers used by DBS?
6 comments
Response to Reviewer 8t7G (Part 2/2)
W2. Additional adaptive baseline and distinction from learned filterbanks and latent targets.
Learnable-filterbank experiment. We implemented the published learnable-filterbank specifications described by Dai et al. (2023) and integrated the front end with BSRNN. The authors' code was unavailable for cross-checking. The −11.7 dB result therefore reflects this particular unsuccessful integration, not a general failure of learnable filterbanks. Appendix J analyzes the causes: analysis–synthesis distortion with the separator bypassed, redundant filters concentrated at low frequencies, and latent-channel ordering incompatible with BSRNN's frequency-ordered processing.
Because this adaptation is not a reliable baseline for comparing learnable front ends, we added SFC-CA (Saijo and Bando, 2026), an input-adaptive spectral-compression method, to Table 3. We evaluated it with the same BSRNN separator, DnR v2 data, training settings, and 128-token budget as DBS.
Table R13. SFC-CA and DBS on DnR v2 (SI-SDR in dB; MACs in GMAC/s).
| Model | Music | Speech | SFX | Avg. | Params (M) | MACs |
|---|---|---|---|---|---|---|
| SFC-CA BSRNN | 6.06 | 14.92 | 4.47 | 8.48 | 4.9 | 48.1 |
| DBS-BSRNN | 6.48 | 15.01 | 5.73 | 9.07 | 4.7 | 48.0 |
DBS exceeds SFC-CA by 0.59 dB at nearly identical MACs (48.035 vs. 48.080 GMAC/s). SFC-CA aggregates spectral features through input-adaptive cross-attention; DBS explicitly predicts contiguous frequency boundaries and uses the same partition for pooling and full-resolution reconstruction.
Distinction from Conv-TasNet and Two-Step Sound Source Separation. Conv-TasNet (Luo and Mesgarani, 2019) jointly learns a waveform encoder/decoder and estimates masks in the encoded representation; its analysis filters are shared across inputs and it does not predict boundaries between contiguous STFT bands. Two-Step Sound Source Separation (Tzinis et al., 2020) learns an encoder/decoder using oracle masks from clean sources, then fixes the transforms and trains a separator to predict latent targets. These works establish the value of learned representations, but do not address mixture-dependent partitioning of contiguous STFT bands under a fixed token budget. DBS uses its predicted partition for both pooling and reconstruction while retaining the separator core. Tables R12 and R13 provide controlled evidence for this specific contribution.
Q1. Static BSRNN with the same refinement modules at matched MACs.
We built a static BSRNN with the same pooling, frequency refinement, and mask reconstruction modules as DBS. Increasing its recurrent hidden dimension from 128 to 137 yielded 48.308 GMAC/s, versus 48.035 GMAC/s for DBS (0.6% difference).
Table R14. Static BSRNN and DBS-BSRNN on DnR v2. Latency is mean ms over 40 runs; memory is peak GPU MB.
| Model | Music | Speech | SFX | Avg. | MACs | Latency | Peak memory |
|---|---|---|---|---|---|---|---|
| Compute-matched static BSRNN | 5.87 | 14.80 | 4.14 | 8.27 | 48.3 | 135.5 | 745.6 |
| DBS-BSRNN | 6.48 | 15.01 | 5.73 | 9.07 | 48.0 | 47.1 | 701.0 |
At matched MACs, DBS improves average SI-SDR by 0.80 dB, reduces mean latency by 65.2%, and reduces peak GPU memory by 6.0%. This supports the contribution of dynamic partitioning beyond the shared refinement and reconstruction modules.
Response to authors
Thank you for the response and the new experiments.
-
The MAC numbers I questioned were the ones in the submission. Thanks for the corrected counts.
-
Thank you for the matched control. It shows that dynamic boundaries add 0.5 to 0.8 dB (Tables 10, R12 and R14). That is about half of the 1.4 dB headline, and the rest comes from the new interface. The abstract still claims a 29.0% relative gain, which is measured against the published BSRNN. Against the static model with the same interface the gain is about 8% so the actual improvment is more marginal and I do not know if that would also wash away with more heavy tuning.
-
If the second decimal implies neither statistical significance nor perceptual discriminability, as you say, it should be dropped. All results are still single runs. Your two static controls, with LSTM hidden size 128 and 137, already differ by 0.6 dB on SFX. Please report several seeds and stats.
-
Since you agree that the learnable filterbank is not a reliable baseline, please remove it from Table 3.
Since you corrected the cost numbers and ran the control I asked for, I am raising my rating to weak rejection. I still find the contribution incremental for ICLR, since it is a change to the band split interface that gives 0.5 to 0.8 dB from single runs.
Response to Reviewer 8t7G (Part 1/2)
We thank the reviewer for the feedback. We address W1–W2 and Q1 below.
W1. Corrected computational cost, adaptive boundaries, and separation gains.
We found errors in the original profiling script: it overcounted LSTM operations and incorrectly counted convolution operations. We corrected the script and recomputed MACs on 3-second clips, normalized by duration, counting one multiply–accumulate as one MAC. The general response gives the full measurement protocol and latency results across all seven model pairs.
Table R11. Corrected MACs (GMAC/s), Static / DBS.
The corrected MAC increases are 14.8% for BSRNN and 29.8% for TIGER on DnR v2, and 2.2%–39.6% on MUSDB18-HQ. Across seven pairs, mean latency changes by −22.2% to +43.4%: it decreases in three pairs, changes by about 2% in two, and has larger increases for BS-RoFormer on MUSDB18-HQ (+43.4%) and BSRNN on EchoSet (+33.6%). DBS-BSRNN improves DnR v2 SI-SDR by 1.38 dB while reducing parameters from 35.5M to 4.7M (87%). DBS-TIGER improves SI-SDR by 1.39 dB. On MUSDB18-HQ, average SDR gains are 0.35, 1.84, and 0.82 dB for BSRNN, BS-RoFormer, and MelRoFormer, respectively.
From fixed bands to mixture-dependent boundaries. BSRNN and BS-RoFormer use predefined frequency boundaries shared across mixtures. DBS predicts input-dependent boundaries while preserving contiguous bands and a fixed token budget. Acoustic transition cues guide Hard Top-K boundary selection within frequency blocks. The resulting partition controls content-weighted pooling and full-resolution complex-mask reconstruction; a local soft-assignment surrogate provides gradients through the separation objective.
Boundary contribution under a shared interface. We trained static controls with the same backbone, pooling, frequency refinement, mask reconstruction, and training settings as DBS. The BSRNN control used a fixed partition; the MelRoFormer control retained its original Mel partition.
Table R12. Static and dynamic partitions with the shared DBS interface (dB).
DBS gains 0.70 dB SI-SDR on DnR v2 (8.374 to 9.07) and 0.54 dB SDR on MUSDB18-HQ (7.53 to 8.07). Thus, gains persist when pooling and reconstruction modules are matched.
Reporting precision and source-wise gains. Two-decimal reporting follows prior comparison tables and does not imply statistical significance or perceptual discriminability. Average scores hide source-wise variation: on DnR v2, gains are 1.65 dB for music, 2.35 dB for SFX, and 0.14 dB for speech. On MUSDB18-HQ, DBS-BS-RoFormer improves SDR by 2.50 dB for vocals, 1.96 dB for drums, and 1.34 dB for bass. These are objective results under the stated evaluation settings; we do not claim perceptual significance.