Pith. sign in

Paper Citation Record · LEDGER

Complexity boosted adaptive training for better low resource ASR performance

As of 15 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2412.00877.

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

pith.paper-citation-record.v1
2412.00877 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T04:59:13.276922Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T04:59:13.181738Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-12T04:59:13.376269Z

Reference resolution

31 of 31 outbound references displayed

  • verified exact3
  • verified fuzzy21
  • unresolved6
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 636cd41e-0758-465e-b063-8dd6dceaa173 · outbound

This paper cites Besides the model architecture, the performance of ASR systems relies heavily on the availability of large and di- verse training data with transcripts.

Complexity boosted adaptive training for better low resource ASR performance Besides the model architecture, the performance of ASR systems relies heavily on the availability of large and di- verse training data with transcripts

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.573176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.174738Z digest=sha256:7f6a985f933a729b115f744d87ac038056db51877826f9a30c4b0f15e4c6ef94

Observation ff154d97-0682-4123-a436-4b9f8037f992 · outbound

This paper cites It introduces feature domain time masking and fre- quency masking to data augmentation.

Complexity boosted adaptive training for better low resource ASR performance It introduces feature domain time masking and fre- quency masking to data augmentation

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.556285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.185534Z digest=sha256:03cb556776ee52ad95e8586c0056f6069bdb568a61351fe9b5da28ffae004373

Observation e5648e41-b9be-4db0-9877-3d03f89ffc10 · outbound

This paper cites The operation of the mask remains at twice in WeNet Conformer.

Complexity boosted adaptive training for better low resource ASR performance The operation of the mask remains at twice in WeNet Conformer

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.545163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.188522Z digest=sha256:9a1d6cbc8822be36e3550c83a095940d076fe288a89cb0c797802573130dfdbb

Observation 093d14bd-31f7-483d-98da-09366a4fec3c · outbound

This paper cites Dataset We perform our experiments on two datasets: AISHELL-1 [23] and LibriSpeech [24].

Complexity boosted adaptive training for better low resource ASR performance Dataset We perform our experiments on two datasets: AISHELL-1 [23] and LibriSpeech [24]

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.536053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.191901Z digest=sha256:aa4d0d20c713fab2fd8ab1cb3a4194dc63e84e3abcbac9c05fd165d36d21e63b

Observation 3b2247d6-730b-4131-84d3-eccbd235d80f · outbound

This paper cites Ini- tially, we apply regularization to the training process by utilizing the intermediate CTC loss regularization.

Complexity boosted adaptive training for better low resource ASR performance Ini- tially, we apply regularization to the training process by utilizing the intermediate CTC loss regularization

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.527524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.195668Z digest=sha256:a8017c3ed91590692769a4d85f154ec0eceb93a288c887daa5595a5bf45763f5

Observation ee2c21b1-a6b2-4eb6-808f-18c1195263a6 · outbound

This paper cites Sapaugment: Learning a sample adaptive policy for data augmentation,.

Complexity boosted adaptive training for better low resource ASR performance Sapaugment: Learning a sample adaptive policy for data augmentation,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.500247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.217649Z digest=sha256:e9278536d156fe9bd1810b317378292611902ad532cc928b8899c81a7a1ad4a8

Observation f47c79d8-4c03-43eb-ba5d-94721ba4c816 · outbound

This paper cites SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition.

Complexity boosted adaptive training for better low resource ASR performance SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.220242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.220242Z digest=sha256:b5b00d93f413f6c8ba7ca0529458b8e4681df0e24e328959ae6e2c57fd290900

Observation deea2ba0-ebb0-4466-8018-9eb2b703880f · outbound

This paper cites Listen, attend and spell: A neural network for large vocab- ulary conversational speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Listen, attend and spell: A neural network for large vocab- ulary conversational speech recognition,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.516535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.199365Z digest=sha256:e8dff1abd6cca59cd3ae230d4ab40b5592204ad7857bda437beb2e514f2c2607

Observation 85c88d28-a3cd-4a5c-8a02-3258efccf081 · outbound

This paper cites Attention-based mod- els for speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Attention-based mod- els for speech recognition,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.507798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.202788Z digest=sha256:e98af358625067159e31f7f1fd4116af2fc0998ec4be0070ce1be4ef70882318

Observation dd44d7b4-33e5-4d48-9003-f1f078178743 · outbound

This paper cites Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation.

Complexity boosted adaptive training for better low resource ASR performance Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.206432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.206432Z digest=sha256:aba056f77e2083424d3eced74720ecf42e480267316339c48d37ecddc7a3a88f

Observation 51b0be4c-6c6f-4a8e-803f-ae6cffdd3263 · outbound

This paper cites ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion.

Complexity boosted adaptive training for better low resource ASR performance ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.210179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.210179Z digest=sha256:56475182e930a1fbc72ec749bde989e58f3cd4c71f8ccf8c90b579398a9419f0

Observation cf33eb89-4f5b-4f1b-a293-1026a3dba7a3 · outbound

This paper cites On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR.

Complexity boosted adaptive training for better low resource ASR performance On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-08-12T04:59:13.354836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.214106Z digest=sha256:0487c472c8d6af9b9f4cab554d097a5fd0e527d0a7c5ec0b134393e1af85701d

Observation bed62a36-acf5-49ae-a377-c4d014c4e75f · outbound

This paper cites An inves- tigation of deep neural networks for noise robust speech recog- nition,.

Complexity boosted adaptive training for better low resource ASR performance An inves- tigation of deep neural networks for noise robust speech recog- nition,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.454160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.239940Z digest=sha256:225871db957115fbae8eaf7a3adaccfe6c91c2a1adaf511387732b91de6a5d70

Observation 04b197bb-a089-47c2-ba0c-e2751d6cd2aa · outbound

This paper cites A study on data augmen- tation of reverberant speech for robust speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance A study on data augmen- tation of reverberant speech for robust speech recognition,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.446515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.242606Z digest=sha256:347b648b72b1caf97493020d60cecaa01b7f683c5d12d2f6b508b06bd17cda48

Observation 7f157ab6-17b3-4134-97db-263c957a0284 · outbound

This paper cites Squeezeformer: An efficient transformer for automatic speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Squeezeformer: An efficient transformer for automatic speech recognition,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.491828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.223821Z digest=sha256:713005bca2ba758ed954addec674a3d84b71e6b01b7a93cd5bbe9e497e81a755

Observation fe585277-334c-40c9-b29e-0d98ae24ea23 · outbound

This paper cites Various aux- iliary loss functions have been explored for different architectures.

Complexity boosted adaptive training for better low resource ASR performance Various aux- iliary loss functions have been explored for different architectures

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.564914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.178375Z digest=sha256:f25ceb6564f97117e0faf219c7f64e47a5664f441b0fd2a815a2f19acf317345

Observation 00bf2ea5-3ed5-40d5-a758-a4ec8bdc38e4 · outbound

This paper cites E-branchformer: Branchformer with enhanced merging for speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance E-branchformer: Branchformer with enhanced merging for speech recognition,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.481827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.227580Z digest=sha256:8e68cc42c085fbe278e0b56431e9d87132204f770d6c5173275eaa701b7b26ec

Observation f4936376-87d1-403d-b090-55eeea420f31 · outbound

This paper cites Complexity boosted adaptive training for better low resource ASR performance.

Complexity boosted adaptive training for better low resource ASR performance Complexity boosted adaptive training for better low resource ASR performance

Reference 18

Resolution
metadata mismatch
local_arxiv, observed 2026-08-12T04:59:13.379242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.181738Z digest=sha256:55eb4a04d2987bf2ab6d82a5c96d4579cbcf11c793625cf884dca23f3d435878

Observation 3e7047f1-e9b6-4e9d-a336-7b7d334137f4 · outbound

This paper cites Improving Mandarin Speech Recogntion with Block-augmented Transformer.

Complexity boosted adaptive training for better low resource ASR performance Improving Mandarin Speech Recogntion with Block-augmented Transformer

Reference 19

Resolution
verified exact
local_arxiv, observed 2026-08-12T04:59:13.336947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.230166Z digest=sha256:5bb9276929169a2d4e1e62868844ba5e88adea46a70c653d864b39ab5edaac08

Observation f1057e79-b45f-4d7e-8f0b-434465ea3e33 · outbound

This paper cites Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition,

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.471945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.233807Z digest=sha256:9602f5a7821139ea36d7ece9474a5bfe808b2412b50f0c94325eea6ee5eaf343

Observation 2d6cc468-aa8c-4f87-b49e-1ff1db78041d · outbound

This paper cites Audio augmentation for speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Audio augmentation for speech recognition,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.463127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.237490Z digest=sha256:e22d5a55de9d97ab58635447259811a37a2bb84cb8a954ec62b4836daca7c2be

Observation 30c59f6a-5d1b-4aa1-b93b-ff1e8a629b24 · outbound

This paper cites Connectionist temporal classification: la- belling unsegmented sequence data with recurrent neural net- works,.

Complexity boosted adaptive training for better low resource ASR performance Connectionist temporal classification: la- belling unsegmented sequence data with recurrent neural net- works,

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.438185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.245586Z digest=sha256:e3611ce6288c9da689cfcdcbbbc24ce8bce9dd22df08aed92ca3480bdccb0546

Observation a714ec34-6ccb-4674-99ad-b714cc59d40f · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Complexity boosted adaptive training for better low resource ASR performance Sequence Transduction with Recurrent Neural Networks

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.248922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.248922Z digest=sha256:df90f6672c23365f9789c4be4bdf1494852302da8ea24506d313e88cc86865bc

Observation 7104b695-2ac3-457c-95a8-c5e2f2cdd21c · outbound

This paper cites Attention is all you need,.

Complexity boosted adaptive training for better low resource ASR performance Attention is all you need,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.427366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.252486Z digest=sha256:624703bc8dd31469bfb913151f1b46e4e54863da6732ea49a369a774ac7b2b2b

Observation e5eca047-f1a5-416d-b76f-83b3f53434b3 · outbound

This paper cites Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition.

Complexity boosted adaptive training for better low resource ASR performance Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition

Reference 25

Resolution
verified exact
local_arxiv, observed 2026-08-12T04:59:13.317205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.256131Z digest=sha256:995067974ad8b450fe2fce202aa73136a73d24d8270e24ba9cea4a19e050a2fe

Observation 87443b2b-e9ba-47bd-8782-f2515900cb7c · outbound

This paper cites Intermediate loss regular- ization for ctc-based speech recognition,.

Complexity boosted adaptive training for better low resource ASR performance Intermediate loss regular- ization for ctc-based speech recognition,

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.416657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.259394Z digest=sha256:e87e36002f73051c38f711888c270ccb625fdc7a8e35dbbb13c9bbd839b0bc57

Observation f7d8372a-6714-47ac-b3f5-77c74528a2ee · outbound

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

Complexity boosted adaptive training for better low resource ASR performance Conformer: Convolution-augmented Transformer for Speech Recognition

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.263015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.263015Z digest=sha256:74b58333142901dec0ee2fa692e2432ccd57209df3f60ed6ce1fc58ce3a33eb3

Observation 6260f095-42ec-4c31-9990-41765f8c7ea3 · outbound

This paper cites WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit.

Complexity boosted adaptive training for better low resource ASR performance WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-12T04:59:13.266712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T04:59:13.266712Z digest=sha256:5113c2d711f68ee58c280f3a846c6db2ab6f9256c71172fc48db5dc913fdf27d

Observation e07e22b5-3586-42d3-849b-3bfa036020b0 · outbound

This paper cites Paris, Incomplete beta functions , NIST Handbook of Mathematical Functions, Cambridge University Press, 2010.

Complexity boosted adaptive training for better low resource ASR performance Paris, Incomplete beta functions , NIST Handbook of Mathematical Functions, Cambridge University Press, 2010

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.406394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.270129Z digest=sha256:4c707b7f91531e93abe8c8b25fd4b1eabada62896be33eab3b23fba1ac01b021

Observation b3d33752-2c54-4efd-909c-cd7dbf79e207 · outbound

This paper cites Aishell-1: An open-source mandarin speech corpus and a speech recognition baseline,.

Complexity boosted adaptive training for better low resource ASR performance Aishell-1: An open-source mandarin speech corpus and a speech recognition baseline,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.396940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.273407Z digest=sha256:28eb780a47996baf83cea100e6cdecce895eda3c5f50ab06ee0e17be71533f59

Observation dd3faef0-191a-4a5e-99d3-7080c5f13a29 · outbound

This paper cites Librispeech: an asr corpus based on public do- main audio books,.

Complexity boosted adaptive training for better low resource ASR performance Librispeech: an asr corpus based on public do- main audio books,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T04:59:13.389175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.276922Z digest=sha256:ead12c4a799cf0af7a6cc5862df2920e946786251c98708c13ff58a331329f1c

Pith citing papers

Observation f4936376-87d1-403d-b090-55eeea420f31 · inbound

Complexity boosted adaptive training for better low resource ASR performance cites this paper.

Complexity boosted adaptive training for better low resource ASR performance Complexity boosted adaptive training for better low resource ASR performance

Reference 18

Resolution
metadata mismatch
local_arxiv, observed 2026-08-12T04:59:13.379242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

source=pdf_text observed=2026-08-12T04:59:13.181738Z digest=sha256:55eb4a04d2987bf2ab6d82a5c96d4579cbcf11c793625cf884dca23f3d435878