Pith. sign in

Paper Citation Record · LEDGER

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2508.10009.

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

pith.paper-citation-record.v1
2508.10009 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T01:05:46.447560Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T01:05:43.913842Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T01:05:46.601121Z

Reference resolution

31 of 31 outbound references displayed

  • verified exact0
  • verified fuzzy21
  • unresolved8
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 586c0fd9-9f91-47e6-b24d-e0a6ec76ebec · outbound

This paper cites Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T01:05:46.690100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:43.913842Z digest=sha256:99c26a2cf56b8c772703cb57a9ff94d6b017675fb316b19fd78bc2d9d3ba34e4

Observation fbb2e7e8-46e7-41d7-b8d2-f8a1c289cea2 · outbound

This paper cites Further details are presented in the following subsections.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Further details are presented in the following subsections

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:50.422775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:43.958842Z digest=sha256:beec6d0c22adb7b38cf1ab059ced59fca50e1dafd03ebdb29d4d96e4ea84e855

Observation e6ec2d64-78eb-446e-a424-3b027d711362 · outbound

This paper cites Datasets 3.1.1.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Datasets 3.1.1

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:50.305824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.019470Z digest=sha256:e9bc4ef04c7aa543750e8a1cc90296f65ac8e65f8ea5471fbdc47e3f11b70696

Observation 0aeff68f-136c-4610-8c23-4e739c4276f6 · outbound

This paper cites Decoder S-MoE To validate the effectiveness of S-MoE applied to the decoder blocks, we conducted experiments on two tasks: Korean-to- English (ko2en) ST and Korean ASR (ko-ASR).

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Decoder S-MoE To validate the effectiveness of S-MoE applied to the decoder blocks, we conducted experiments on two tasks: Korean-to- English (ko2en) ST and Korean ASR (ko-ASR)

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:50.012876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.179893Z digest=sha256:52ad224628c6a408a1d80ec2fbdf92f2b464865a6e5057ed50788e0cd98de0a4

Observation 8aa07d1d-aefc-43ca-bda8-c453b431af92 · outbound

This paper cites By us- ing guiding tokens instead of dynamic gating functions, S-MoE ensures efficient training and inference while improving per- formance across various tasks.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts By us- ing guiding tokens instead of dynamic gating functions, S-MoE ensures efficient training and inference while improving per- formance across various tasks

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:49.696543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.304450Z digest=sha256:721b839de15553c6115fdf880bc4ba7e4f5457b728af5a28936911099f9bbb02

Observation d9e30dc1-fdae-407f-aa2d-6e8400a5ed5a · outbound

This paper cites Sources of degradation of speech recognition in the telephone network,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Sources of degradation of speech recognition in the telephone network,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:49.372762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.870745Z digest=sha256:4acc4b56bafee4ca9bd9f58378091ad6dd411e7ab5afd6e783b4849e79024728

Observation 52a8f881-d60d-4db8-ad6b-d52e9d955011 · outbound

This paper cites Training wideband acoustic mod- els using mixed-bandwidth training data for speech recognition,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Training wideband acoustic mod- els using mixed-bandwidth training data for speech recognition,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:49.194971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.974020Z digest=sha256:872a2df26a6f95ca4ed85990be658b8577832cf63bffd90ba2c0f73b5397d45e

Observation ad7de39c-ef70-43ce-85c2-34c2e3cdf340 · outbound

This paper cites Multi-Task Learning with Deep Neural Networks: A Survey.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Multi-Task Learning with Deep Neural Networks: A Survey

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:44.392830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:44.392830Z digest=sha256:002c01a62988cf8017aa4716a5ee277a4ea69e2283465ff3a4205506392b00c8

Observation 8b4dfa92-13ca-4b43-b161-c2d33b5e5357 · outbound

This paper cites An Overview of Multi-Task Learning in Deep Neural Networks.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts An Overview of Multi-Task Learning in Deep Neural Networks

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:44.487656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:44.487656Z digest=sha256:2b5a1384e469949e5e69433a246f854ad83a337695f9150ded3261a586366d19

Observation 3df0ff5c-f5c7-4ec8-9e47-2ad73d12ec50 · outbound

This paper cites A survey on multi-task learning ieee transactions on knowledge and data engineering,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts A survey on multi-task learning ieee transactions on knowledge and data engineering,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:49.508010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.579694Z digest=sha256:80802cbbfced2030ef0c7e71895890abdb0ff7cb0fe16ec0014e804c7ecb741b

Observation 13ecb848-b814-4af7-853b-f9a0e5895d14 · outbound

This paper cites Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:44.679323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:44.679323Z digest=sha256:53e6551387feb712bec69588a18e9245f4ef4d9a35ac3898c4dba8dbee8e3571

Observation b14f26aa-863c-4f9f-8fb7-d577a9f976d5 · outbound

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

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:44.775645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:44.775645Z digest=sha256:08b5ccb95216c986433c15a89f83a8ae946849746be4a5264c2477a8f44b0625

Observation acd40c53-6442-45f1-b63d-2d5296943386 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:48.012664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.460528Z digest=sha256:a1cc78b5bcab53e8d17af9e30077d4d078a498c072400394d3a6800e9c590825

Observation 1ffa1fea-0693-407b-934a-1c9022565ecd · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:47.877416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.556818Z digest=sha256:d794a78bd3fb414b2854d30f3285de1d55a89465d92d04dd31aa18549dc28c00

Observation eaeb04fd-c4b1-4509-9e5f-27669a752e2d · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:49.060196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.073418Z digest=sha256:aefcc54ddbc1a267cb8aca77bbc1d8ff5e550cee540a0688ff5c357e2b241d9b

Observation bed821b7-7dc2-48d8-8567-32de69b8f85a · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:48.848835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.170383Z digest=sha256:add2d90bf1c160bad221af62242488f7953b6d61441f66b965589f30139cbe5f

Observation f46f5ba2-6f3d-4384-b665-a628fc6e8ef8 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:48.642320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.264475Z digest=sha256:b8aa5f82533d48ee2622fc8adbc2597ea5bb8794845901807b74d14d116fb0bf

Observation d5367c58-a785-4998-84df-386c5f577384 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:48.440198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.321574Z digest=sha256:40592bdbaeaa95d8b25a381507852f93e0add4980246cb7106853bcb13c45ef6

Observation db6ba20b-e15a-44fb-8a18-ec018b8b582e · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:48.164816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.394744Z digest=sha256:62e99a2dc9370e93c2bdfcc2fc47b9280011a6841043c5f1ca127fe1fc8b6ad0

Observation 072708d6-4e41-4654-a0ed-d3ab503c465a · outbound

This paper cites Pulse code modulation (pcm) of voice fre- quencies,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Pulse code modulation (pcm) of voice fre- quencies,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:46.982149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:46.071817Z digest=sha256:2101f2f79c7286944e79ca56a045b4b49204e45ae78a0fb3d5d4f3dd3b7ca6e7

Observation 33a791ee-bc8a-4d32-8f6d-292134b25192 · outbound

This paper cites Our in-house test sets consist of 1,000 samples of male and female speech from daily conversations, with refer- ence translations curated by professional translators.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Our in-house test sets consist of 1,000 samples of male and female speech from daily conversations, with refer- ence translations curated by professional translators

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:50.162275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.122596Z digest=sha256:b51dc374e4c3a140235b3f305b82c8d20bd82ae42ffeefe114dbf66685149903

Observation aa6474cd-aa62-4796-975f-820f642c40e4 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:47.654187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.618663Z digest=sha256:5be11b138bc939b26dd2f016a0340769aca8b6a98a87d4bfb269e80a65839fa0

Observation a1f6a03c-ea88-490c-be24-e1e607f20541 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:47.474698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.683072Z digest=sha256:1c445593e8fec0f492670884cc439ccfbb1ac390d675ffeb35a97c791d0f2645

Observation 38a3220f-17f0-4c27-8d6f-3a9caec67139 · outbound

This paper cites Whisper is a widely used mul- tilingual speech model trained with diverse language pairs.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Whisper is a widely used mul- tilingual speech model trained with diverse language pairs

Reference 24

Resolution
malformed identifier
raw_fallback, observed 2026-08-06T01:05:49.880492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:44.239321Z digest=sha256:0517dcd937216358730d8c288b72fc0af5a9715ad06b32ca245b248aff3d9408

Observation 49206302-ec76-4c0c-8fc2-e0053d1bb54b · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:47.280919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.783547Z digest=sha256:811b88610ec2999a0c66396c1cb5ce699297227ff51f639442009f11ed6537d1

Observation c4cad7bc-fb68-44ec-99b9-fde756a834a2 · outbound

This paper cites [Online].

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts [Online]

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:47.116778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:45.863666Z digest=sha256:783e57a016e5707d76d893fe54da80b5e62abdc254c4f5f8c3012aecec16d14c

Observation e2fefd12-a43e-47c1-9e49-927204004dd2 · outbound

This paper cites The adaptive multirate wideband speech codec (amr-wb),.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts The adaptive multirate wideband speech codec (amr-wb),

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:45.952971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:45.952971Z digest=sha256:ebb0c73fc0e1c8c21e1b84a11dd344a739bc8454743fc6381f120166d84a5918

Observation ad761f03-d506-4a96-bd8f-686fc5e454ef · outbound

This paper cites Fleurs: Few-shot learning evaluation of universal representations of speech,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Fleurs: Few-shot learning evaluation of universal representations of speech,

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:46.175496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:46.175496Z digest=sha256:38b75aa6f8300a0c2da6aa579a357684a8130f0a613a9d1098d527916345fbae

Observation 29b34952-b47b-4dee-9584-9a971a3bf21d · outbound

This paper cites Attention is all you need,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Attention is all you need,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T01:05:46.876936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:46.281915Z digest=sha256:63ef78fda9600aea1d1a3c5ae687092c11d4bf8098d095b0b248f917e6595c3e

Observation bd80abc3-b9aa-49ce-9548-76222386d705 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Bleu: a method for automatic evaluation of machine translation,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:46.369512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:46.369512Z digest=sha256:b92639dea274046f5422404691e063e46967426b62a83f2d927d938c66e099f0

Observation 2be105f0-24c8-4d44-b516-90f8e82b548b · outbound

This paper cites Robust speech recognition via large-scale weak supervision,.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Robust speech recognition via large-scale weak supervision,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T01:05:46.447560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T01:05:46.447560Z digest=sha256:1f3ea01ea58d16e2c082087bf3197e46cde338f6e21c11f641dd6e3e4269c949

Pith citing papers

Observation 586c0fd9-9f91-47e6-b24d-e0a6ec76ebec · inbound

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts cites this paper.

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T01:05:46.690100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

source=pdf_text observed=2026-08-06T01:05:43.913842Z digest=sha256:99c26a2cf56b8c772703cb57a9ff94d6b017675fb316b19fd78bc2d9d3ba34e4