Paper Citation Record · LEDGER

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation

As of 8 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 2 inbound Pith citation observations for arXiv:2606.29575.

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

pith.paper-citation-record.v1
2606.29575 v2

Coverage vector

measured 52 of 52 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:43:18.529912Z

measured 54 of 54 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:43:18.529912Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T06:45:29.367148Z

Reference resolution

52 of 52 outbound references displayed

verified exact7
verified fuzzy39
unresolved4
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e6bdcb03-3d7e-49f1-8ba0-fa76002198ba · outbound

This paper cites an unresolved cited work.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-07-06T17:22:42.701663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9c25bd13-8341-48dd-b5d8-ecc1691689b4 · outbound

This paper cites an unresolved cited work.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-07-06T17:22:42.703352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e9fe71ca-07c1-4974-b595-c86bc9efce50 · outbound

This paper cites It outperforms Conformer backbone by +1.3 dB SDR on Libri2Mix.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation It outperforms Conformer backbone by +1.3 dB SDR on Libri2Mix

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.707028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2638f79b-dd46-41dd-9d5f-eea451d805a5 · outbound

This paper cites TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T06:45:29.369256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 22e30953-743e-4192-ab0d-a74d39a83a77 · outbound

This paper cites an unresolved cited work.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-07-06T17:22:42.699881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9fea5f9d-f721-4b21-a5e4-35643479c4ce · outbound

This paper cites Experimental Setup Datasets & Configuration:Experiments are conducted on the Libri2Mix (16kHz, min) dataset from LibriMix [33].

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Experimental Setup Datasets & Configuration:Experiments are conducted on the Libri2Mix (16kHz, min) dataset from LibriMix [33]

Reference 6

Resolution: malformed identifier; raw_fallback, observed 2026-07-06T17:22:42.696205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8cb20a3f-be0c-4bab-8e83-373a31f4dbfd · outbound

This paper cites free lunch.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation free lunch

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.693960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 09bc1c4a-19f2-49b9-ab21-a88b68d2db3d · outbound

This paper cites 2021ZD0201500, in part by the Na- tional Natural Science Foundation of China under Grant No.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation 2021ZD0201500, in part by the Na- tional Natural Science Foundation of China under Grant No

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.698105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41efa208-211d-4c59-b3e9-5509fa59f773 · outbound

This paper cites an unresolved cited work.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-07-06T17:22:42.667077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d72f451-dc52-4258-ac50-67dbefa3e498 · outbound

This paper cites Supervised speech separation based on deep learning: An overview,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Supervised speech separation based on deep learning: An overview,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.665136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a060dcca-96d1-4e5b-a177-8bfeee5166b4 · outbound

This paper cites Permutation invari- ant training of deep models for speaker-independent multi-talker speech separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Permutation invari- ant training of deep models for speaker-independent multi-talker speech separation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.668977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cfe5070b-5c33-40ce-aa7e-32d282016010 · outbound

This paper cites Conv-TasNet: Surpassing Ideal Time– Frequency Magnitude Masking for Speech Separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Conv-TasNet: Surpassing Ideal Time– Frequency Magnitude Masking for Speech Separation,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.671337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 62fc2e2a-b232-41a4-ba0a-08ed95ef3d51 · outbound

This paper cites Speech Enhancement with Score-Based Generative Models in the Complex STFT Do- main,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Speech Enhancement with Score-Based Generative Models in the Complex STFT Do- main,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.673536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1efc57f2-7adc-49c2-a185-70a00572f7ad · outbound

This paper cites Tf-gridnet: Making time-frequency domain models great again for monaural speaker separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Tf-gridnet: Making time-frequency domain models great again for monaural speaker separation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.682208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7f3113c3-af2a-4636-92bb-bfabd4bb6eb6 · outbound

This paper cites Efficient Monaural Speech Enhancement with Universal Sample Rate Band-Split RNN,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Efficient Monaural Speech Enhancement with Universal Sample Rate Band-Split RNN,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.661407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a23962fe-c28d-40c4-9cb3-1df1da2dd740 · outbound

This paper cites URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.663284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e540235f-95c9-49a1-ac50-ed36a0b80c52 · outbound

This paper cites Interspeech 2025 URGENT Speech Enhancement Challenge,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Interspeech 2025 URGENT Speech Enhancement Challenge,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.655465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2025c1e7-218a-4139-935f-104b4d67ea1b · outbound

This paper cites The VoicePrivacy 2024 Challenge Evaluation Plan.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation The VoicePrivacy 2024 Challenge Evaluation Plan

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:45:29.365647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 352e27d3-a482-4b65-bb30-51651a9380f6 · outbound

This paper cites Icassp 2023 deep noise suppression challenge.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Icassp 2023 deep noise suppression challenge

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.659371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a7030cc5-44ab-4f0a-8ba8-adaaca0fc8b6 · outbound

This paper cites TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:45:29.372738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 58a325aa-63f2-4d8f-9784-f19f6fc4bec4 · outbound

This paper cites Low latency speech enhancement for hearing aids using deep filtering,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Low latency speech enhancement for hearing aids using deep filtering,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.657547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation acee32c5-c30c-4724-a7fa-eab2d8836aed · outbound

This paper cites Dual-Path RNN: Effi- cient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Dual-Path RNN: Effi- cient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.680156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e980fec2-275d-435a-bbd6-17b47edb5635 · outbound

This paper cites Attention Is All You Need In Speech Separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Attention Is All You Need In Speech Separation,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.682384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 71616630-ddbd-431b-96a1-15ee4ff3023a · outbound

This paper cites Skim: Skipping Mem- ory Lstm for Low-Latency Real-Time Continuous Speech Sepa- ration,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Skim: Skipping Mem- ory Lstm for Low-Latency Real-Time Continuous Speech Sepa- ration,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.640260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eed9bb51-482f-440b-938e-b8d321c35fac · outbound

This paper cites Tiger: Time-frequency in- terleaved gain extraction and reconstruction for efficient speech separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Tiger: Time-frequency in- terleaved gain extraction and reconstruction for efficient speech separation,

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:45:29.354783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e485f9e-8ea3-486b-8b54-7ba61e825eb5 · outbound

This paper cites Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech En- hancement,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech En- hancement,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.638391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a93a9248-f5e2-4e49-8208-cdb73201cc5a · outbound

This paper cites Beyond Performance Plateaus: A Comprehensive Study on Scal- ability in Speech Enhancement,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Beyond Performance Plateaus: A Comprehensive Study on Scal- ability in Speech Enhancement,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.642132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c26d042b-fc7c-494e-8765-efb10f8f3e45 · outbound

This paper cites Predictive Skim: Contrastive Pre- dictive Coding for Low-Latency Online Speech Separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Predictive Skim: Contrastive Pre- dictive Coding for Low-Latency Online Speech Separation,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.646127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 349d987b-b216-4308-8066-c6368cca18ca · outbound

This paper cites CheapNET: Improving Light- weight speech enhancement network by projected loss function,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation CheapNET: Improving Light- weight speech enhancement network by projected loss function,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.651688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 15a1d461-48e4-473a-b6e8-469c79153fd8 · outbound

This paper cites TF-SkiMNet: Speech En- hancement Based on Inplace Modeling and Skipping Memory in Time-Frequency Domain,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation TF-SkiMNet: Speech En- hancement Based on Inplace Modeling and Skipping Memory in Time-Frequency Domain,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.649859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 485b3d45-3a63-492b-8e5e-7da92ceea371 · outbound

This paper cites A Comprehensive Survey of Mixture-of- Experts: Algorithms, Theory, and Applications,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation A Comprehensive Survey of Mixture-of- Experts: Algorithms, Theory, and Applications,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.636306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6fd3653b-1171-4c42-919e-10d53c54c109 · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.653570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ff84f60-5111-45f1-a180-7f202e30944c · outbound

This paper cites Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.711163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 707fda9f-314b-4d5b-af4e-46d19f2fbce0 · outbound

This paper cites GLaM: Efficient Scaling of Language Models with Mixture-of-Experts,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation GLaM: Efficient Scaling of Language Models with Mixture-of-Experts,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.719120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 288eac4a-980b-4f0e-83c5-bed488126fb8 · outbound

This paper cites DeepSeekMoE: Towards Ulti- mate Expert Specialization in Mixture-of-Experts Language Mod- els,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation DeepSeekMoE: Towards Ulti- mate Expert Specialization in Mixture-of-Experts Language Mod- els,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.692043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c7f0d85e-ade8-43b9-bc01-0f5c8a7a4848 · outbound

This paper cites CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.705228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6dddedf2-8092-447f-ab6f-a919d1a70032 · outbound

This paper cites Speech Enhance- ment using a Deep Mixture of Experts,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Speech Enhance- ment using a Deep Mixture of Experts,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.689992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc858a76-c567-4351-98c3-bd58b5b6cace · outbound

This paper cites Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.686181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b365e67-ae60-45a2-945a-7dddb7546a58 · outbound

This paper cites A Scale for the Measurement of the Psychological Magnitude Pitch,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation A Scale for the Measurement of the Psychological Magnitude Pitch,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.684217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e8e6d430-81cd-4ca0-a40e-b229ebc0b3b4 · outbound

This paper cites Conformer: Convolution-augmented Transformer for Speech Recognition,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Conformer: Convolution-augmented Transformer for Speech Recognition,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.688213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 590972de-2458-4b21-ba1c-d4341df231ec · outbound

This paper cites Searching for Activation Functions.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Searching for Activation Functions

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-01T06:45:29.348006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation afb0a471-a3a4-4815-aeca-b8c5ce8cb592 · outbound

This paper cites Librimix: An open-source dataset for generalizable speech separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Librimix: An open-source dataset for generalizable speech separation,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.709240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 674c83ed-c825-406f-b155-f4bb980f302a · outbound

This paper cites Decoupled Weight Decay Regularization.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Decoupled Weight Decay Regularization

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-01T06:45:29.351339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 737f54a6-aea7-49c5-8d19-67c075c4184f · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-01T06:45:29.358465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b72fee9-50eb-44db-a84f-077bc8a9e360 · outbound

This paper cites BSS EV AL Toolbox User Guide – Revision 2.0,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation BSS EV AL Toolbox User Guide – Revision 2.0,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.720973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c16e7bf1-1d84-41f8-9e41-5e79008a78eb · outbound

This paper cites SDR – Half-baked or Well Done?.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation SDR – Half-baked or Well Done?

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.717139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cd962c50-1199-4971-8396-ccc56f6101c4 · outbound

This paper cites Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.676335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d229ec3b-aa7a-4f92-a138-1ae474ad1ea9 · outbound

This paper cites An Algo- rithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation An Algo- rithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.647943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1709d252-903c-4401-aa35-54fd857c15e2 · outbound

This paper cites SPMamba: State-space model is all you need in speech separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation SPMamba: State-space model is all you need in speech separation,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.678203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ea21dbd1-832e-4210-b3db-574ce032d89f · outbound

This paper cites Speech separation using an asynchronous fully recurrent convolutional neural network,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Speech separation using an asynchronous fully recurrent convolutional neural network,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.713170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 791d7164-b7f4-4b4d-be55-260e3967fbcc · outbound

This paper cites An efficient encoder-decoder architecture with top-down attention for speech separation.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation An efficient encoder-decoder architecture with top-down attention for speech separation

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:45:29.362282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 850466b8-b9ec-468f-b392-634889b54993 · outbound

This paper cites Sudo rm-rf: Efficient net- works for universal audio source separation,.

TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation Sudo rm-rf: Efficient net- works for universal audio source separation,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T17:22:42.715387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation b27ee8f9-5f64-4e6e-bd02-0483bb5e525e · inbound