Paper Citation Record · LEDGER

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution

As of 8 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2607.18658.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.18658 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T14:47:16.214424Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T14:47:14.238419Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 098ec478-e828-4094-927b-0a434f2d313c · outbound

This paper cites Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.238419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8946a9f-599c-4e39-9ca1-b97321429d58 · outbound

This paper cites Input features are stacked along the channel dimension, and inter-channel infor- mation is fused within the layer to form the output [10, 11].

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Input features are stacked along the channel dimension, and inter-channel infor- mation is fused within the layer to form the output [10, 11]

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.352723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7c58c4f-3c7b-4ef2-a909-b10a3e5f4752 · outbound

This paper cites an unresolved cited work.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.514726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33da09ee-1385-4128-8cde-6f2716fe0b55 · outbound

This paper cites Impact of Fixed vs.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Impact of Fixed vs

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-01T14:47:14.612712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc53ebb-4071-4bae-8c25-ec5b0461489d · outbound

This paper cites an unresolved cited work.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.681917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24026e50-30ee-4d1b-8b3b-c5c9ff09940d · outbound

This paper cites U25A20409, and in part by SJTU Med-X (Medicine & Engineering) Translational Research Grant (YG2025LC09).

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution U25A20409, and in part by SJTU Med-X (Medicine & Engineering) Translational Research Grant (YG2025LC09)

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.834046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52c68b56-89a5-475d-abdc-eee3a1c64aed · outbound

This paper cites All scientific content, ideas, analysis, and conclusions are original and fully authored by the researchers.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution All scientific content, ideas, analysis, and conclusions are original and fully authored by the researchers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:14.939236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf94a1e9-040c-43ae-b338-f2b2324bd4a8 · outbound

This paper cites SenSE: Semantic-aware high-fidelity universal speech enhancement,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution SenSE: Semantic-aware high-fidelity universal speech enhancement,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.019958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0119d4b-071c-4600-936b-06704a5ae9f2 · outbound

This paper cites DNN-based geometry- invariant DOA estimation with microphone positional encoding and complexity gradual training,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution DNN-based geometry- invariant DOA estimation with microphone positional encoding and complexity gradual training,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.390874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a464dd8f-b77b-4de0-ab51-d6efcb5eb7f6 · outbound

This paper cites AnyEnhance: A unified generative model with prompt-guidance and self-critic for voice enhancement,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution AnyEnhance: A unified generative model with prompt-guidance and self-critic for voice enhancement,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.086359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef4b40e5-5d89-49fc-b7e3-c9eddc8c7901 · outbound

This paper cites End-to- end microphone permutation and number invariant multi-channel speech separation,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution End-to- end microphone permutation and number invariant multi-channel speech separation,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.122307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f1eb3e5-6f50-4b62-9055-b8ff512afca5 · outbound

This paper cites TPARN: Triple-path attentive recurrent network for time-domain multichannel speech enhancement,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution TPARN: Triple-path attentive recurrent network for time-domain multichannel speech enhancement,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.164002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc288d78-d7a0-4a3a-8079-e20bad8b2841 · outbound

This paper cites Improving design of in- put condition invariant speech enhancement,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Improving design of in- put condition invariant speech enhancement,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.211397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be6a1abf-efc3-44d1-8af0-8d8d993f8aba · outbound

This paper cites AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics Encoding and Dropout-Based Learning.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics Encoding and Dropout-Based Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.259938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cb14ad-d358-44fe-9541-771eef592f21 · outbound

This paper cites UniArray: Unified spectral-spatial modeling for array-geometry-agnostic speech separation,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution UniArray: Unified spectral-spatial modeling for array-geometry-agnostic speech separation,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.309007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc8cdf1d-f9fb-4cd8-b90f-c15c70256534 · outbound

This paper cites A memory-based gravitational search al- gorithm for enhancing minimum variance distortionless response beamforming,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution A memory-based gravitational search al- gorithm for enhancing minimum variance distortionless response beamforming,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.359868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 072a0c16-3ecf-4eaa-89e4-925c094e5186 · outbound

This paper cites TF-GridNet: Integrating full- and sub-band modeling for speech separation,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution TF-GridNet: Integrating full- and sub-band modeling for speech separation,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.855365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40156162-b37a-49e7-8b50-685bfab7869b · outbound

This paper cites Beam-TasNet: Time-domain audio separation net- work meets frequency-domain beamformer,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Beam-TasNet: Time-domain audio separation net- work meets frequency-domain beamformer,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.438047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e9a9017-c9e1-4178-9e8c-ca7181aa7e4e · outbound

This paper cites Closing the gap between time-domain multi-channel speech enhancement on real and simulation conditions,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Closing the gap between time-domain multi-channel speech enhancement on real and simulation conditions,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.485664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331ef254-5a55-4017-8117-a10402d06f1f · outbound

This paper cites NeRF: Representing scenes as neural radiance fields for view synthesis,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution NeRF: Representing scenes as neural radiance fields for view synthesis,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.534881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a38d113-4b79-4837-b8d7-6aa3718ee59a · outbound

This paper cites Learning neural acoustic fields,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Learning neural acoustic fields,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.583084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8299703-9838-4b1d-a987-bb6a06621bdd · outbound

This paper cites RealMAN: A real-recorded and anno- tated microphone array dataset for dynamic speech enhancement and localization,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution RealMAN: A real-recorded and anno- tated microphone array dataset for dynamic speech enhancement and localization,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.630613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 977a3356-433a-417d-91bc-b68b2e2b5161 · outbound

This paper cites Music source separation with band-split RNN,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Music source separation with band-split RNN,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.652676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af068860-f786-4829-a3f4-2b8b79e39dd7 · outbound

This paper cites SpatialNet: Extensively learning spatial in- formation for multichannel joint speech separation, denoising and dereverberation,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution SpatialNet: Extensively learning spatial in- formation for multichannel joint speech separation, denoising and dereverberation,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.752642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c04689f-25dd-40f7-bdd7-cb111c83085d · outbound

This paper cites A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.959730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76cf895f-face-4ba1-9885-1ff2a040aa81 · outbound

This paper cites Perceptual eval- uation of speech quality (PESQ)-a new method for speech qual- ity assessment of telephone networks and codecs,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution Perceptual eval- uation of speech quality (PESQ)-a new method for speech qual- ity assessment of telephone networks and codecs,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:16.007853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57113d2b-aaf9-4e63-b171-e60f8e85d21a · outbound

This paper cites A short- time objective intelligibility measure for time-frequency weighted noisy speech,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution A short- time objective intelligibility measure for time-frequency weighted noisy speech,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:16.088061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 253f46ee-39c4-4ef6-9434-9587487874d2 · outbound

This paper cites DNSMOS P. 835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution DNSMOS P. 835: A non- intrusive perceptual objective speech quality metric to evaluate noise suppressors,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:16.154364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e124e135-f9e1-4c42-9816-27b2d9e4b232 · outbound

This paper cites An analysis of environment, microphone and data simulation mismatches in robust speech recognition,.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution An analysis of environment, microphone and data simulation mismatches in robust speech recognition,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:16.214424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee406369-01f1-4329-a644-908167f022c2 · outbound

This paper cites SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement.

Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T14:47:15.050474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 098ec478-e828-4094-927b-0a434f2d313c · inbound