SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living

Debolina Chowdhury; Suman Samui; Sujoy Saha

Dataset	Domain	Bathroom	Public	Non-target class	Raw-waveform baselines
ESC-50 [ 29 ]	Environmental	✗	✓	✗	✗
UrbanSound8K [ 32 ]	Urban	✗	✓	✗	✗
AudioSet [ 12 ]	General	Partial	✓	✗	✗
Chen et al. [ 5 ]	Bathroom	✓	✗	✗	✗
Hyun [ 15 ]	Water/bathroom	✓	✗	✗	✗
Öztürk et al. [ 26 ]	Restroom	✓	✓	✗	✗

Table 1 : Representative datasets for environmental sound recognition and bathroom monitoring. SnaanGhar7 adds mobility-aid events, an explicit non-target class, and raw-waveform edge baselines.

Figure 1 : Assistive-living use scenario of SnaanGhar7 . The selected sound classes represent bathroom activities relevant to an older adult living independently. Door and walker/crutch sounds provide entry, exit, and mobility cues, while tap, shower, and flush-related sounds correspond to common hygiene activities.

Property	Value
Classes	7
Recording environments	5 (residential, hostel, institutional)
Contributors	3
Original duration	$\approx$ 385 min
Total segmented windows	21,387
Clip duration	1.51125 s (30,225 samples)

Table 2 : Summary of the SnaanGhar7 dataset and its embedded recording platform.

Class	Description	Acoustic characteristics
Flush	Toilet flushing	Broadband water flow with transient onset
Shower	Shower water flow	Continuous broadband noise
Bathroom Tap	Bathroom tap running	Continuous water flow, varying intensity
Basin Tap	Basin tap running	Localized continuous water flow
Door	Opening/closing/knocking	Short impulsive sounds
Walker/Crutch	Mobility-aid movement	Repeated transient impacts

Table 3 : Class definitions and dominant acoustic characteristics.

Figure 2 : Embedded recording platform used for data acquisition.

ID	Location	Type
E01	NIT Durgapur	Institutional
E02	Residential Home, Howrah	Residential
E03	Hall-6, NIT Durgapur	Hostel
E04	DS-1B, NIT Durgapur	Residential
E05	Hall-9, NIT Durgapur	Hostel

Table 4 : Recording environments.

Figure 3 : Overview of the SnaanGhar7 data collection, annotation, preprocessing, and benchmark-generation pipeline.

Figure 4 : Class distribution of the SnaanGhar7 dataset.

Figure 5 : Signal-level statistics per class (violin plots). Impulsive classes ( Door , Walker/Crutch ) show markedly higher kurtosis and zero-crossing rate than the sustained water classes, providing a purely time-domain axis of separation that a raw-waveform model can exploit.

Figure 6 : Per-class mean power spectra. The sustained water classes ( Flush , Shower , Bathroom Tap ) overlap in the mid-frequency band, foreshadowing the model’s principal confusions, whereas impulsive classes carry distinct high-frequency transient energy.

Figure 7 : Representative mel-spectrogram per class. Impulsive events ( Door , Walker/Crutch ) appear as brief vertical onset stripes; the sustained water classes fill the window with visually similar broadband energy, previewing their confusability.

Figure 8 : Per-class temporal energy profile. Impulsive events ( Door , Walker/Crutch ) show a sharp onset and decay; sustained water events maintain a flat envelope. The onset structure gives a time-domain cue that complements the overlapping spectra of Fig. 6 .

Figure 9 : Per-class spectral descriptors (centroid, bandwidth, roll-off, flatness). Impulsive classes show higher centroids and flatness; sustained water classes cluster at lower centroids with smoother spectra, separating the two families along the same axis the model exploits.

Figure 10 : Within-class variability per class. The sustained water classes are internally variable (flow rate, basin geometry) as well as mutually overlapping, whereas impulsive classes are tighter. The combination of high intra-class spread and high inter-class overlap that makes the water triad the hardest group.

Class	$D_{c}$	Mean overlap	Intra spread
Flush	0.74	0.50	0.92
Door	0.54	0.42	0.79
Basin Tap	0.45	0.46	0.81
Shower	0.43	0.47	0.83
Walker/Crutch	0.31	0.38	0.77
Bathroom Tap	0.25	0.42	0.76

Table 5 : Per-class difficulty ranking from the signal-level analysis (higher

=

predicted harder), computed before model training. The aggregate score is a heuristic: its class-level correlation with model error is weak (

\rho=-0.07

), while pairwise overlap is more useful for explaining specific confusions (Section 7.7 ).

Figure 11 : Per-class difficulty profiles across the five component diagnostics of Eq. ( 2 ) (inter-class overlap, intra-class spread, class imbalance, silence fraction, energy variability). Each class is hard for a different combination of reasons; Flush scores high on both overlap and spread, while the impulsive classes are driven by silence and energy variability.

Figure 12 : Linear-discriminant projection of the hand-crafted feature space. Impulsive classes and Basin Tap separate cleanly, while the sustained water classes overlap even under the best linear projection, an intrinsic, model-independent property of the acoustics.

Figure 13 : SincDPNet architecture. A learnable sinc filter bank, parameterized by per-filter cutoff and bandwidth in Hz, maps the raw waveform to

N_{f}

band-pass channels. A depthwise-separable convolutional body then performs classification. The front end contains only

2N_{f}

trainable parameters.

Component	Parameters	Share
Sinc front-end ( $2N_{f}$ )	50	1.76%
Depthwise-separable body + head	2,798	98.24%
Total	2,848	100%

Table 6 : Parameter budget of the compact SincDPNet (

N_{f}=25

). The filter-bank parameter count is independent of kernel length

L

.

Figure 14 : Quality-based coreset construction. (a) Distribution of the composite quality score across training clips; the top

25\%

per class is retained for search. (b) Validation macro-F1 for the same candidate architectures under coreset and full-data training. The reported rank correlation indicates how well the coreset preserves the ordering used during optimization.

Variable	Symbol	Range	Primarily affects
Sinc filters	$N_{f}$	$16$ – $128$	size, F1, resolution
Sinc kernel length	$L$	$101$ – $401$ (odd)	latency, F1
Body width mult.	$\alpha$	$2$ – $12$	size (dominant)
DS-conv blocks	$B$	$3$ – $6$	size, latency
Peak LR	$\eta$	$10^{-3}$ – $3\!\times\!10^{-2}$	F1 (convergence)
Pooling stride	$s$	$\{2,4,8\}$	latency, F1

Table 7 : Design variables for the MOBO case study.

Figure 15 : Hypervolume versus evaluation for Study A. The surrogate-guided configurations reach similar final hypervolume values and outperform random search within the fixed evaluation budget.

Config	Acquisition	Kernel	Final HV	Evals to 90%
C1	qEHVI	Matérn-5/2	2091.27	17
C2	qNEHVI	Matérn-5/2	2090.65	18
C3	qParEGO	Matérn-5/2	2089.43	22
C4	qEHVI	RBF	2090.12	19
C5	Random	—	2078.49	$>24$

Table 8 : Acquisition and kernel sensitivity for Study A at a fixed budget of 24 model evaluations. Higher final hypervolume (HV) is better, while “Evals to 90%” indicates the evaluations required to reach 90% of the best HV gain. Best values are shown in bold .

Figure 16 : Pareto fronts from the two design studies. Dominated configurations are shown faded; points are colored by weighted score, and the highest-F1 and highest weighted-score selections are marked.

Rank	Architecture			Performance		Selection
	$N_{f}$	$\alpha$	$B$	Size (KB)	Macro-F1	Weighted	Pareto
1	78	4	5	13.3	0.8443	0.8523	$\star$
2	25	6	4	11.1	0.8016	0.7842	$\star$
3	24	8	5	36.7	0.8592	0.7698	$\star$
4	20	2	3	1.4	0.7622	0.7574	$\star$
5	24	3	5	7.9	0.7783	0.7562	$\star$

Table 9 : Study-A configurations ranked according to the weighted score.

N_{f}

denotes the number of sinc filters,

\alpha

denotes the width multiplier, and

B

denotes the number of depthwise-separable blocks. A

\star

indicates a Pareto-optimal configuration in the Macro-F1–model-size plane. Bold values indicate the best overall values.

Model	Input	Params	Acc. (%)	Bal. Acc.	Macro-F1	MCC
DS-CNN [ 36 ]	MFCC	18,311	75.3 $\pm$ 6.8	0.811 $\pm$ 0.053	0.705 $\pm$ 0.063	0.715 $\pm$ 0.071
CRNN [ 3 ]	MFCC	236,967	74.6 $\pm$ 4.3	0.826 $\pm$ 0.024	0.695 $\pm$ 0.027	0.709 $\pm$ 0.041
TinyCNN [ 36 ]	MFCC	93,575	76.5 $\pm$ 7.4	0.809 $\pm$ 0.058	0.698 $\pm$ 0.070	0.729 $\pm$ 0.076
SincNet [ 30 ]	Raw	132,327	76.7 $\pm$ 1.8	0.809 $\pm$ 0.027	0.712 $\pm$ 0.013	0.721 $\pm$ 0.023
ACDNet [ 24 ]	Raw	22,055	71.7 $\pm$ 3.0	0.729 $\pm$ 0.032	0.639 $\pm$ 0.033	0.670 $\pm$ 0.028
DPNet [ 6 ]	Raw	4,944	69.3 $\pm$ 2.0	0.689 $\pm$ 0.016	0.612 $\pm$ 0.009	0.645 $\pm$ 0.020

Table 10 : Performance comparison on SnaanGhar7 under environment-disjoint splitting. Results are reported as mean

\pm

standard deviation over three random seeds. Parameter counts are exact. The best result in each metric is shown in bold.

Figure 17 : Test-set t-SNE embeddings of the two configurations selected by the search. The best-F1 model (a) uses more capacity and pulls the water classes slightly further apart, while the compact rank-1 model (b) keeps the same overall layout at a fraction of the size. In both, the impulsive classes separate cleanly and the sustained water classes share one region, so the structure is preserved across the trade-off.

ID	Variant	Macro-F1	$\Delta$ vs. A0
A0	SincDPNet (reference: $N_{f}=25$ , $L=401$ )	0.651 $\pm$ 0.049	0.000
A1a	Fixed (non-learnable) sinc front-end	0.644 $\pm$ 0.046	$-0.007$
A1b	Plain trainable conv front-end	0.615 $\pm$ 0.051	$-0.036$
A1c	MFCC + same body	0.636 $\pm$ 0.044	$-0.015$
A2a	$N_{f}=16$	0.613 $\pm$ 0.052	$-0.038$
A2b	$N_{f}=32$	0.628 $\pm$ 0.047	$-0.023$

Table 11 : Component ablations under environment-disjoint splitting (macro-F1, mean

\pm

standard deviation over three seeds).

\Delta

denotes the change in mean macro-F1 relative to A0. Best macro-F1 is shown in bold .

Figure 18 : Learned SincDPNet filter bank (each bar is one band-pass filter; width

=

bandwidth). The learned allocation of spectral resolution is directly readable in Hz.

Figure 19 : Overlaid magnitude responses of the full learned filter bank on a shared frequency axis. The dense overlap in the low-to-mid band and the sparse coverage of the high band show, in a single view, how the bank concentrates spectral resolution where the water classes carry their energy.

Figure 20 : Frequency-magnitude responses of the learned sinc filters. The band-pass channels tile the low-to-mid frequency range densely and the high range sparsely, the frequency-domain view of the allocation in Fig. 18 .

Figure 21 : Per-class mean activation energy across learned filters. Sustained water classes share active bands (explaining their confusability), whereas Basin Tap and impulsive classes occupy distinct bands.

Figure 22 : Per-class activation traced across individual learned filters. The sustained water classes activate nearly the same filters, while the impulsive classes and Basin Tap each drive a separable group, mirroring the confusion structure of Fig. 24 .

Figure 23 : Acoustic-to-model comparison for the compact

N_{f}=25

model. Left: the aggregate class-difficulty score has little association with class error. Right: pairwise acoustic overlap has a modest positive association with off-diagonal confusion.

Figure 24 : Row-normalized (recall, %) confusion matrices of the two configurations selected by the multi-objective search. The best-F1 model (a) recovers Basin Tap and Door , the classes the compact model sacrifices, at the cost of

12\times

more footprint; the rank-1 weighted model (b) preserves the easy classes at 13.3 KB but leaves Basin Tap unresolved. Added capacity is spent precisely on the hardest, most overlapping classes.

Figure 25 : Pairwise Bhattacharyya overlap (Eq. 1 ) between class feature distributions (

1=

identical). The sustained water classes form the highest-overlap block, providing the a priori prediction that the trained model later confirms in its confusion matrix (Fig. 24 ).

Figure 26 : t-SNE embeddings of the held-out test set for all benchmarked models. The sustained water classes form a single overlapping region in every model regardless of size, while the impulsive classes and Basin Tap stay separated, evidence that the confusability structure is a property of the data, not of any one architecture.

Selection role	$N_{f}$	$\alpha$	Blocks	Val. macro-F1	Size (KB)
Highest weighted score (rank-1)	78	4	5	0.8443	13.3
Highest validation F1	59	10	5	0.8942	54.8
Compact Pareto model	25	6	4	0.8016	11.1

Table 12 : Study-A configurations selected for deployment-aware evaluation. The three configurations represent distinct points on the Pareto frontier: best weighted score (rank-1), highest validation macro-F1, and a compact model.

Device (RAM, clock)	Model	Params	Acc. (%)	Macro-F1	Inf. time	RTF
Raspberry Pi Zero 2 W ( $512$ MB, $1$ GHz)	DPNet (baseline)	4,944	69.2	0.612	15 ms	0.01
	SincDPNet, compact ( $N_{f}{=}25$ )	2,848	75.7	0.661	435.6 ms	0.29
	SincDPNet, best-F1	14,040	80.2	0.760	920.4 ms	0.61
	SincDPNet, rank-1 (weighted)	3,408	75.6	0.673	886.3 ms	0.59
Laptop (Intel Core U5) ( $16$ GB, $1.2$ GHz)	DPNet (baseline)	4,944	69.2	0.612	2.5 ms	0.0016
	SincDPNet, compact ( $N_{f}{=}25$ )	2,848	75.7	0.661	28.0 ms	0.0186

Table 13: Single-clip inference performance of DPNet and selected SincDPNet configurations on embedded and reference hardware for a

1.5

s audio clip. Inference time excludes audio capture; RTF

<1

indicates faster-than-real-time operation.

Error category	Count
Transient/impulsive overlap	774
Broadband water-flow ambiguity	406
Non-target/unknown confusion	29
Low SNR / background masking	0
Annotation-boundary (partial event capture)	0
Total	1,209

Table 14: Error characterization of the deployed SincDPNet over its

T=1{,}209

misclassified test clips, assigned to mutually exclusive categories by an automated rule-based audit (each clip is counted once, under the first matching rule). Two acoustic categories account for

97.6\%

of all errors.

SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living

Abstract

Figures & tables

Explore similar work

Bad: Taming the Bioacoustic Data Deluge with a Bat Activity Detector

Smart Passive Acoustic Monitoring: Embedding a Classifier on AudioMoth Microcontroller

Towards Deployable Underwater Vessel Classification