Pith. sign in

Paper Citation Record · LEDGER

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning

As of 10 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2608.05549.

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

pith.paper-citation-record.v1
2608.05549 v1

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:07:57.395550Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T11:07:57.206713Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-08T11:07:57.528503Z

Reference resolution

44 of 44 outbound references displayed

  • verified exact0
  • verified fuzzy26
  • unresolved16
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1dd38b13-3188-4a19-97dc-6dde6dfb7308 · outbound

This paper cites Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-08T11:07:57.533202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.206713Z digest=sha256:d4ad84018c9c1e0be66af4b5967b6c2b444b93b4d286beaed2d892777ed9b25c

Observation 52628428-2130-40f7-aab9-2fdc35063895 · outbound

This paper cites Energy Conservation.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Energy Conservation

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.917978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.211954Z digest=sha256:057ef2fdf2eab43872ee77f9daf00cf429ab37f5099daaa73f5929cf31d8ef76

Observation 72eca95a-9459-448c-8b4a-319050730c4d · outbound

This paper cites Datasets Training data.We used the V oxCeleb2 development set [28] (5,994 speakers) for training.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Datasets Training data.We used the V oxCeleb2 development set [28] (5,994 speakers) for training

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.906371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.216364Z digest=sha256:f4e51b6a93cf3cc0956706574a270646d6a22d6fd8799148bb863fafde0b2108

Observation 79817a95-d120-4c51-a579-d1bad95e3b6b · outbound

This paper cites Performance on VoxCeleb and VoxSRC21-val Table 1 summarizes the results on the V oxCeleb1 test sets (V oxCeleb1-O/E/H).

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Performance on VoxCeleb and VoxSRC21-val Table 1 summarizes the results on the V oxCeleb1 test sets (V oxCeleb1-O/E/H)

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.882575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.224784Z digest=sha256:c0231ff58b4a3958ed6529326e902c4b30322b4b504f56b3f0355a0aac552b31

Observation e68ef3ba-5296-48ee-9122-283c767cfb8e · outbound

This paper cites an unresolved cited work.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-08T11:07:57.870249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.229625Z digest=sha256:d70a7a4d185c4c6f9a5a5def17a623a357ae899214c45b971c605e8365880d70

Observation 4d411026-bcb4-4657-ad22-5b76430c6a44 · outbound

This paper cites 15228223), and The Hong Kong Polytechnic University, Project ID P0049192.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning 15228223), and The Hong Kong Polytechnic University, Project ID P0049192

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.857166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.233833Z digest=sha256:b7585f9cdc7a6ac7844642c107e376763f598faea8e8561b0c23bfda755e1539

Observation 9ff43e43-ca7b-4950-930e-123c733451b9 · outbound

This paper cites All scientific content, experiments, anal- yses, and conclusions were produced and verified by the au- thors.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning All scientific content, experiments, anal- yses, and conclusions were produced and verified by the au- thors

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.844509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.238913Z digest=sha256:bab92b6e6f855a3c1fee9b79ff270d7c03e060deca9f369f0f6fa3f27b6bb238

Observation 0f0ab25f-64d7-4e47-9558-8dc4eb5381fe · outbound

This paper cites Distilling attention knowledge for speaker verifica- tion,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Distilling attention knowledge for speaker verifica- tion,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.757959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.273579Z digest=sha256:0ef24ba79d4093ec0e3f5ecafdbae31fa9b15dc655b1edbdf93bd761dc753bcd

Observation 33c9df49-c152-4fbd-af6a-3fb99f9b6398 · outbound

This paper cites Deep residual learning for image recognition,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Deep residual learning for image recognition,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.243320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.243320Z digest=sha256:b9c44141d0451094520bdd4d77e18f5f5cfb7fd5122d57f5fda985567b4d55c9

Observation 9e952269-0feb-4e61-b39f-1841a1b883cd · outbound

This paper cites Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Ecapa-tdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.247181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.247181Z digest=sha256:5029afb8ca60524dfa28e721fa512f03b9bd53b8b5e68f50789c419e2ad6f944

Observation aacbbd98-6bf5-4606-af7d-c07821c92387 · outbound

This paper cites Uncertainty- aware multi-head multi-mode knowledge distillation for self- supervised speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Uncertainty- aware multi-head multi-mode knowledge distillation for self- supervised speaker verification,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.818026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.251308Z digest=sha256:0930e69bda99aee261d767f61f0f9b4660cd39bb15f65f0d1e4db45ca7e322db

Observation 034f5033-5823-496b-8aa5-b442ec68ea92 · outbound

This paper cites Adversar- ially adaptive temperatures for decoupled knowledge distillation with applications to speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Adversar- ially adaptive temperatures for decoupled knowledge distillation with applications to speaker verification,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.806562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.256019Z digest=sha256:502117fdbf46127284e8d6aa75f3c12224a1e1079ddf5e17aa837d3767262109

Observation 96879738-d80d-41e2-922e-2d72d8385e07 · outbound

This paper cites W-GVKT: Within-global-view knowledge transfer for speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning W-GVKT: Within-global-view knowledge transfer for speaker verification,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.795528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.260735Z digest=sha256:c0762c9058b3556d4b7d867cccb2ec690f1bde87f766126589c776cc8f79a3d1

Observation e42aa549-0700-43b5-97a1-7bf47dd585f1 · outbound

This paper cites De- noising student features with diffusion models for knowledge dis- tillation in speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning De- noising student features with diffusion models for knowledge dis- tillation in speaker verification,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.782864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.264986Z digest=sha256:431773ad2b965692ae301786257eb3da8957f45feb3fb51f840874f0bbb0bf33

Observation 0ad7daee-80d0-4867-adb4-4adee12f7c61 · outbound

This paper cites Disentangling speech representations learning with latent dif- fusion for speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Disentangling speech representations learning with latent dif- fusion for speaker verification,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.770090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.269194Z digest=sha256:35f10aa25447bb6135eb4ed18cfacc15bd4ef5b626139876b8f45ce2fe598c16

Observation 46fdee72-2480-4b96-a9f4-1460996488a3 · outbound

This paper cites Residual networks be- have like ensembles of relatively shallow networks,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Residual networks be- have like ensembles of relatively shallow networks,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.698731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.308812Z digest=sha256:02bd3c447600b230d5cc1f96ead4da810a06ecbf4e97e413323ef320634ad85a

Observation bad4f119-8726-4e86-93f4-ae7990a9d96d · outbound

This paper cites Vision Transformer: Vit and its Derivatives.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Vision Transformer: Vit and its Derivatives

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.278288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.278288Z digest=sha256:c47fa0098926b4cc6d1f02af65400695687f8e671dcbd95100a243ba3b8ded19

Observation 87be2885-6d47-41d1-92cd-b52c57cb2825 · outbound

This paper cites Varia- tional regularization for end-to-end speech deepfake detection,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Varia- tional regularization for end-to-end speech deepfake detection,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.746531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.282497Z digest=sha256:9ac39879e5de2020db4853f5d80c0868fab349f1338015cc598dd300776307ca

Observation ee91c684-8f48-428a-aa97-fa9582c0bcc5 · outbound

This paper cites Self-supervised learning with multi-head multi-mode knowledge distillation for speaker verifi- cation,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Self-supervised learning with multi-head multi-mode knowledge distillation for speaker verifi- cation,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.734870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.286901Z digest=sha256:b544cc8542e8d0b994f8627a16980f1ff02714d00c99462a9f6c3e80d3fc6206

Observation a55f87af-d3af-4933-b639-a3b7f5f7653c · outbound

This paper cites An enhanced res2net with local and global feature fusion for speaker verification,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning An enhanced res2net with local and global feature fusion for speaker verification,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.723240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.291161Z digest=sha256:39e67941e7d0e8c0a18568d528ead3665dd66b16cbf4330b6475c10cccaf8277

Observation 04018e0a-02d7-4b87-a3eb-fd454c41be5e · outbound

This paper cites Res2net: A new multi-scale backbone architecture,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Res2net: A new multi-scale backbone architecture,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.296253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.296253Z digest=sha256:510302546fa495a06a80ec810a2bd4091cf6571f17e2454debd5d47e6d601b79

Observation 8d6ef923-4a1a-44bd-bb89-905a3cce3dcc · outbound

This paper cites Densely connected convolutional networks,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Densely connected convolutional networks,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.300342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.300342Z digest=sha256:bd5bedb16e153aa1af0178e7f037445c83bfa216c73a2b8aa414a4b4abf3b656

Observation 53e260e9-167e-4c04-8d4b-8ee5ea699bc0 · outbound

This paper cites Reducing Overfitting in Deep Networks by Decorrelating Representations.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Reducing Overfitting in Deep Networks by Decorrelating Representations

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.304435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.304435Z digest=sha256:85f911554a0fe9afc69faf4fbdb3b90b81b6f076d90954e8a884b9036de355b1

Observation 0e43f093-596e-4bbc-80b6-f888ffb6cdd3 · outbound

This paper cites mHC: Manifold-Constrained Hyper-Connections.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning mHC: Manifold-Constrained Hyper-Connections

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.344776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.344776Z digest=sha256:eb83d8aa2e23c3f0865e069ff738491d56aa9ae1c0376eb9a58b413a639786a3

Observation 4ac3c6f7-2cf4-48f1-87f6-41244f43a477 · outbound

This paper cites Attention is all you need,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Attention is all you need,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.312990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.312990Z digest=sha256:d6dcc1ee3b1d242fb77a450593664eada7369755fd3f6c0b1d31d29e0eb9b1ec

Observation e1ea1503-44ce-448e-9a8a-7ff23bb79929 · outbound

This paper cites Trink: Ink generation with trans- former network,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Trink: Ink generation with trans- former network,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.679786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.317502Z digest=sha256:2dd0b2817999799792afcc9c1b70ee3bfb6dd126d765b24ef6fda96ac7bc2ae3

Observation cff66a71-9826-4f4b-ab3f-9be8e2e5e90c · outbound

This paper cites Language Models are Few-Shot Learners.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Language Models are Few-Shot Learners

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.321962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.321962Z digest=sha256:2b191305d2788898b94be4bd17062f929c5dc74e9f752255e6a135e757967a0d

Observation e118af91-95b2-4564-905d-3219fd1b0237 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.326856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.326856Z digest=sha256:8d7f6c34dd1a4df76e39579b8c2ea3876861eeb3d0175c090649b437fe6e13f1

Observation 71470e64-bdab-4a87-8b48-be01dd0050b1 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning LLaMA: Open and Efficient Foundation Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.331494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.331494Z digest=sha256:1d01297a899051ac9a5498b52389dc595226c56f350b74bc54cd800ba1c57a1c

Observation 33dbe446-7ea8-45ce-8ea4-1653dcc9e469 · outbound

This paper cites Mm-nodeformer: Node transformer multimodal fusion for emotion recognition in conver- sation,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Mm-nodeformer: Node transformer multimodal fusion for emotion recognition in conver- sation,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.667242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.335631Z digest=sha256:e893ebb1d920d5671d84bfb75a4df793cce761162e41f87b7eb9ca6fdba5614d

Observation 8f275bec-6ae0-47e1-ad4e-3a586ee03ba7 · outbound

This paper cites Repeated patterns of gamma-ray flares suggest structured jets of blazars as likely neutrino sources.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Repeated patterns of gamma-ray flares suggest structured jets of blazars as likely neutrino sources

Reference 31

Resolution
metadata mismatch
local_arxiv, observed 2026-08-08T11:07:57.460265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.340177Z digest=sha256:f30e217bd40e93856ce8644e250985fb8e9dd1d6b2b2139d504fedf55b2177b1

Observation 79713c6b-f85e-43cb-b05a-8e55174552f1 · outbound

This paper cites A study on data augmentation of reverberant speech for robust speech recognition,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning A study on data augmentation of reverberant speech for robust speech recognition,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.377483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.377483Z digest=sha256:a6f1f63fedd9299ab2bd55de70a938513023529eb004469380335151545f0c75

Observation 6005fce8-08b9-444a-b436-274f26f80c0e · outbound

This paper cites The small model (ECAPA-S) uses a channel size of 512 and contains 6.19M parameters.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning The small model (ECAPA-S) uses a channel size of 512 and contains 6.19M parameters

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.894295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.220434Z digest=sha256:b72d3289d77a9a3e4143035d0fdccb00fca0e9e2e2427a227794bc2055040ca4

Observation 545b82b9-3ea8-4e89-b1fa-77d3ec7cb1f1 · outbound

This paper cites DeepCrossAttention: Supercharging transformer residual connections,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning DeepCrossAttention: Supercharging transformer residual connections,

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.653933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.349122Z digest=sha256:4665b1dbd7cce30e04bcf90f727e5827290c475f2d91dbe3f7ef2e6bb9655574

Observation 3954ddf3-3571-4bac-aca8-a9da9719a4d6 · outbound

This paper cites Hyper-connections,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Hyper-connections,

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.641546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.353557Z digest=sha256:e0713ae0366919f76a38fe92d997175fb3879ea0f58ee300175ed3e9fb67452e

Observation 197189de-c0a2-4115-be94-30f2cdd0ed3c · outbound

This paper cites Concerning nonnegative matrices and doubly stochastic matrices,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Concerning nonnegative matrices and doubly stochastic matrices,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.357990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.357990Z digest=sha256:736e0d8d677fb0b8d6281868ea52cab6524cf2771b5c5a2a92545791c3cc392c

Observation 7699dfe5-a581-4d68-9ee8-be53a9ded476 · outbound

This paper cites V oxceleb2: Deep speaker recognition,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning V oxceleb2: Deep speaker recognition,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.361760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.361760Z digest=sha256:f80b5799ae1b492d85676d0edea505c513740b2332f33f3f6757179543a29593

Observation 3689d328-b610-443a-a396-cfd6f8592334 · outbound

This paper cites V oxceleb: a large- scale speaker identification dataset,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning V oxceleb: a large- scale speaker identification dataset,

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.616613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.365722Z digest=sha256:07f07bab3ee4736f7c6aae0dfcfda158208eff8935d6c7807e2335b27ef3b03f

Observation 56354843-df14-4263-bc10-89174d69a4e1 · outbound

This paper cites The Kaldi speech recog- nition toolkit,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning The Kaldi speech recog- nition toolkit,

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.605015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.369453Z digest=sha256:cb54c432b6a837d5e44e9878983545a788c9bd828a3ce63103ded8da0b6aaa60

Observation 61401e37-6337-423b-9159-652bc79203c5 · outbound

This paper cites MUSAN: A Music, Speech, and Noise Corpus.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning MUSAN: A Music, Speech, and Noise Corpus

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-08T11:07:57.373294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-08T11:07:57.373294Z digest=sha256:b24342ad73eaa6cf7fd16fc200475588ceee0a8d151e7940b8e4f173ef82eaee

Observation ec887738-3fa0-418c-ace3-2be74462c335 · outbound

This paper cites A time delay neural network architecture for efficient modeling of long temporal con- texts,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning A time delay neural network architecture for efficient modeling of long temporal con- texts,

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.584397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.381738Z digest=sha256:95b127d21cbae3fe5e38d42500671bdb4c25e14aedc1da55a8407a1d621701a0

Observation 3c91fec8-171a-4e48-930c-78ef0d543b0f · outbound

This paper cites Squeeze-and-excitation networks,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Squeeze-and-excitation networks,

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.571762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.386476Z digest=sha256:b9edce68c6df7dc1bc36ff2cd7bce5e2f08a48d2accdd342483bede609c4f998

Observation cda7a5ea-8729-4a00-9b58-9f2275d29eb0 · outbound

This paper cites Arcface: Additive an- gular margin loss for deep face recognition,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Arcface: Additive an- gular margin loss for deep face recognition,

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.558941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.390789Z digest=sha256:c954aab4aa80f62ed1a546cf183e137fdccfc5bcbb241faa2a30cb3033b97269

Observation 4477e4aa-918f-4fa3-84af-101ab24da298 · outbound

This paper cites 3d-speaker-toolkit: An open-source toolkit for multimodal speaker verification and di- arization,.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning 3d-speaker-toolkit: An open-source toolkit for multimodal speaker verification and di- arization,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T11:07:57.546549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.395550Z digest=sha256:30be7f15ad1293bfa46fbcd5474b68b0b6dcd436377acc7651f236aba3e1c6af

Pith citing papers

Observation 1dd38b13-3188-4a19-97dc-6dde6dfb7308 · inbound

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning cites this paper.

Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-08T11:07:57.533202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-08T11:07:57.206713Z digest=sha256:d4ad84018c9c1e0be66af4b5967b6c2b444b93b4d286beaed2d892777ed9b25c