Paper Citation Record · LEDGER

Two-stage Training for Chinese Dialect Recognition

As of 16 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:1908.02284.

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

pith.paper-citation-record.v1
1908.02284 v2

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T15:01:16.555691Z

measured 40 of 40 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 2026-08-14T15:01:16.377171Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-14T15:01:16.687824Z

Reference resolution

39 of 39 outbound references displayed

verified exact4
verified fuzzy26
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6ead2451-9bce-4003-aa0f-3ccc3293a7b0 · outbound

This paper cites The task intro- duced in this paper is more challenging than general LID tasks cause we use a dialect database which contains 10 dialects in China.

Two-stage Training for Chinese Dialect Recognition The task intro- duced in this paper is more challenging than general LID tasks cause we use a dialect database which contains 10 dialects in China

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.379680Z

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.

Observation 47b215e4-6637-459c-8e7d-654e89d74798 · outbound

This paper cites Our system won the ﬁrst place in Xunfei (iFlyTek) Chi- nese Dialect Recognition Challenge, which attracted 110 teams joining in.

Two-stage Training for Chinese Dialect Recognition Our system won the ﬁrst place in Xunfei (iFlyTek) Chi- nese Dialect Recognition Challenge, which attracted 110 teams joining in

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.359988Z

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.

Observation 701631c9-b205-49eb-8d6e-774b9000df65 · outbound

This paper cites an unresolved cited work.

Two-stage Training for Chinese Dialect Recognition Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-14T15:01:17.345639Z

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.

Observation fda61e7c-a312-42e3-ae30-2c9db2ba8c01 · outbound

This paper cites We train an AM in the ﬁrst stage and then use the intermediate features from the AM as inputs to train an RNN to compute posteriors for LID in the second stage.

Two-stage Training for Chinese Dialect Recognition We train an AM in the ﬁrst stage and then use the intermediate features from the AM as inputs to train an RNN to compute posteriors for LID in the second stage

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.326663Z

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.

Observation 7de4b081-06c0-4f1c-9435-bd020cefff9f · outbound

This paper cites The results show that the per- formance is slightly worse than the two-stage system.

Two-stage Training for Chinese Dialect Recognition The results show that the per- formance is slightly worse than the two-stage system

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.307132Z

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.

Observation 2a0840a6-30dc-4433-b868-c2fefa4add3c · outbound

This paper cites Two-stage Training for Chinese Dialect Recognition.

Two-stage Training for Chinese Dialect Recognition Two-stage Training for Chinese Dialect Recognition

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-14T15:01:16.693215Z

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.

Observation 2aa1133f-fd74-4d64-a831-45eaec3045ae · outbound

This paper cites Network structure The major network structure we use in the two-stage system can be divided to the CNN part and the RNN part, as described in Table 1.

Two-stage Training for Chinese Dialect Recognition Network structure The major network structure we use in the two-stage system can be divided to the CNN part and the RNN part, as described in Table 1

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.288424Z

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.

Observation 53e78f20-6f27-454e-92c0-8fe00d0ea287 · outbound

This paper cites an unresolved cited work.

Two-stage Training for Chinese Dialect Recognition Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-14T15:01:17.271228Z

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.

Observation d01bd610-87d3-40ad-a76c-7246bd6394ba · outbound

This paper cites an unresolved cited work.

Two-stage Training for Chinese Dialect Recognition Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-14T15:01:17.252502Z

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.

Observation 32eb63fb-12c8-4a54-bd3b-388593e64b74 · outbound

This paper cites The system links the different stages by using inter- mediate features extracted by a shallow ResNet14 architecture.

Two-stage Training for Chinese Dialect Recognition The system links the different stages by using inter- mediate features extracted by a shallow ResNet14 architecture

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.230559Z

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.

Observation d2c3f59f-d860-4061-b380-9fa6bd5200d4 · outbound

This paper cites Deep neural network approaches to speaker and language recognition,.

Two-stage Training for Chinese Dialect Recognition Deep neural network approaches to speaker and language recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.215778Z

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.

Observation c9e53584-0ce9-48b3-a745-1bfed40b1e2b · outbound

This paper cites Multi- lingual bottleneck features for language recognition,.

Two-stage Training for Chinese Dialect Recognition Multi- lingual bottleneck features for language recognition,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.191471Z

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.

Observation c7fd27ad-112e-4eeb-823c-09297667a8f6 · outbound

This paper cites Neural network bottleneck features for language identiﬁcation,.

Two-stage Training for Chinese Dialect Recognition Neural network bottleneck features for language identiﬁcation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.172323Z

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.

Observation 8ce030ea-6782-4997-a12b-f668764a12a3 · outbound

This paper cites Deep bottleneck features for spoken language identiﬁca- tion,.

Two-stage Training for Chinese Dialect Recognition Deep bottleneck features for spoken language identiﬁca- tion,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.150410Z

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.

Observation 38cabba7-0b8b-479e-bb6d-650f717262eb · outbound

This paper cites Automatic lan- guage identiﬁcation using deep neural networks,.

Two-stage Training for Chinese Dialect Recognition Automatic lan- guage identiﬁcation using deep neural networks,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.134162Z

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.

Observation 25a5ea2c-dd80-40d8-96d4-14224bed1d48 · outbound

This paper cites An end-to-end approach to language identiﬁcation in short utterances using convolutional neural networks,.

Two-stage Training for Chinese Dialect Recognition An end-to-end approach to language identiﬁcation in short utterances using convolutional neural networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.120001Z

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.

Observation 610746a5-533f-42e8-9a23-792ab79ffea9 · outbound

This paper cites End-to- end language identiﬁcation using high-order utterance representa- tion with bilinear pooling,.

Two-stage Training for Chinese Dialect Recognition End-to- end language identiﬁcation using high-order utterance representa- tion with bilinear pooling,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.096902Z

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.

Observation c6b2873d-9abd-4290-98a8-e8ad2c024812 · outbound

This paper cites Stacked long-term tdnn for spoken language recognition.

Two-stage Training for Chinese Dialect Recognition Stacked long-term tdnn for spoken language recognition

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.062705Z

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.

Observation 15333647-c19d-4cce-bcda-e36ecfc4ca05 · outbound

This paper cites Automatic language identiﬁcation using long short-term memory recurrent neural networks,.

Two-stage Training for Chinese Dialect Recognition Automatic language identiﬁcation using long short-term memory recurrent neural networks,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.048482Z

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.

Observation c6cc72f2-6cb2-4e32-9cc4-768eec94c82e · outbound

This paper cites End-to-end language identiﬁcation using attention-based recurrent neural net- works,.

Two-stage Training for Chinese Dialect Recognition End-to-end language identiﬁcation using attention-based recurrent neural net- works,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.033027Z

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.

Observation 2d237bf2-aab5-49c1-8c61-7b71f4b7010e · outbound

This paper cites Spoken language identiﬁcation us- ing lstm-based angular proximity.

Two-stage Training for Chinese Dialect Recognition Spoken language identiﬁcation us- ing lstm-based angular proximity

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:17.009396Z

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.

Observation 3cda4dda-c0ea-40f3-ab3d-b7adb392a583 · outbound

This paper cites Utterance-level end-to-end language identification using attention-based CNN-BLSTM.

Two-stage Training for Chinese Dialect Recognition Utterance-level end-to-end language identification using attention-based CNN-BLSTM

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-14T15:01:16.671066Z

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.

Observation e7396277-f534-4987-9a69-967e729e997f · outbound

This paper cites Dnn based embeddings for language recognition,.

Two-stage Training for Chinese Dialect Recognition Dnn based embeddings for language recognition,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.986180Z

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.

Observation d93739c8-bb97-436e-a958-f9e33114faa7 · outbound

This paper cites Phonetic tempo- ral neural model for language identiﬁcation,.

Two-stage Training for Chinese Dialect Recognition Phonetic tempo- ral neural model for language identiﬁcation,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.961151Z

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.

Observation e166b4de-9300-4cc7-98d2-3c28d92ccff4 · outbound

This paper cites Parallel pho- netically aware dnns and lstm-rnns for frame-by-frame discrimi- native modeling of spoken language identiﬁcation,.

Two-stage Training for Chinese Dialect Recognition Parallel pho- netically aware dnns and lstm-rnns for frame-by-frame discrimi- native modeling of spoken language identiﬁcation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.942427Z

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.

Observation 5eb65ffe-a846-441d-8069-1fb904dcb9a5 · outbound

This paper cites Using deep neural networks for identiﬁcation of slavic languages from acoustic signal,.

Two-stage Training for Chinese Dialect Recognition Using deep neural networks for identiﬁcation of slavic languages from acoustic signal,

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-08-14T15:01:16.920699Z

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.

Observation d666fbfc-354f-4b52-8318-0d4845f970a5 · outbound

This paper cites Con- nectionist temporal classiﬁcation: labelling unsegmented se- quence data with recurrent neural networks,.

Two-stage Training for Chinese Dialect Recognition Con- nectionist temporal classiﬁcation: labelling unsegmented se- quence data with recurrent neural networks,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T15:01:16.500452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7a87b33-988e-4e5c-884f-4560e3e7a2b2 · outbound

This paper cites Deep neural networks for acoustic modeling in speech recognition,.

Two-stage Training for Chinese Dialect Recognition Deep neural networks for acoustic modeling in speech recognition,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T15:01:16.505441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93537fc-1da7-4048-9abd-bec13afa870b · outbound

This paper cites Speech recognition with deep recurrent neural networks,.

Two-stage Training for Chinese Dialect Recognition Speech recognition with deep recurrent neural networks,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.850624Z

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.

Observation 67b5a38e-5c7c-4f4d-a9e1-b6ff2509ad0f · outbound

This paper cites Towards end-to-end speech recognition with recurrent neural networks,.

Two-stage Training for Chinese Dialect Recognition Towards end-to-end speech recognition with recurrent neural networks,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T15:01:16.518442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e414a26f-3b42-418d-bac4-aefdc14c0b44 · outbound

This paper cites Deep speech 2: End-to-end speech recognition in english and mandarin,.

Two-stage Training for Chinese Dialect Recognition Deep speech 2: End-to-end speech recognition in english and mandarin,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.819122Z

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.

Observation 6888215e-bcb5-4506-8cb6-f6d2c6a6bf7d · outbound

This paper cites An end-to-end trainable neural net- work for image-based sequence recognition and its application to scene text recognition,.

Two-stage Training for Chinese Dialect Recognition An end-to-end trainable neural net- work for image-based sequence recognition and its application to scene text recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.796682Z

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.

Observation e01513bc-c6ec-474b-a59e-66f2e435eaf8 · outbound

This paper cites Towards end-to-end speech recognition with deep convolutional neural networks,.

Two-stage Training for Chinese Dialect Recognition Towards end-to-end speech recognition with deep convolutional neural networks,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.767374Z

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.

Observation 450a176d-934e-4275-9215-8664de92407c · outbound

This paper cites Residual Convolutional CTC Networks for Automatic Speech Recognition.

Two-stage Training for Chinese Dialect Recognition Residual Convolutional CTC Networks for Automatic Speech Recognition

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-14T15:01:16.645132Z

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.

Observation 9c8e098c-a806-476f-bf67-3f9e46a53322 · outbound

This paper cites Residual lstm: Design of a deep recurrent architecture for distant speech recognition,.

Two-stage Training for Chinese Dialect Recognition Residual lstm: Design of a deep recurrent architecture for distant speech recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.742642Z

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.

Observation 478a67f2-fc0a-4b6e-9e5f-5d1331216799 · outbound

This paper cites Deep residual learning for image recognition,.

Two-stage Training for Chinese Dialect Recognition Deep residual learning for image recognition,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-14T15:01:16.542909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6244140-4fff-41ae-91b3-deb84957f51a · outbound

This paper cites Bidirectional recurrent neu- ral networks,.

Two-stage Training for Chinese Dialect Recognition Bidirectional recurrent neu- ral networks,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T15:01:16.712639Z

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.

Observation 4d031886-f171-4e72-8fb1-cde93a0bdc40 · outbound

This paper cites Speaker embedding extraction with phonetic information,.

Two-stage Training for Chinese Dialect Recognition Speaker embedding extraction with phonetic information,

Reference 38

Resolution: verified exact; doi, observed 2026-08-14T15:01:16.600865Z

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.

Observation 55f82807-bb7f-450c-bac3-13c2ad3eac49 · outbound

This paper cites Training Multi-Task Adversarial Network for Extracting Noise-Robust Speaker Embedding.

Two-stage Training for Chinese Dialect Recognition Training Multi-Task Adversarial Network for Extracting Noise-Robust Speaker Embedding

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-14T15:01:16.555691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2a0840a6-30dc-4433-b868-c2fefa4add3c · inbound