Paper Citation Record · LEDGER

Two-Pass End-to-End Speech Recognition

As of 16 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 3 inbound Pith citation observations for arXiv:1908.10992.

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

pith.paper-citation-record.v1
1908.10992 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T10:34:37.975728Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T10:34:37.819273Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T23:35:46.389381Z

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy29
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9b160a93-c91a-4aa0-b995-8647289cd942 · outbound

This paper cites an unresolved cited work.

Two-Pass End-to-End Speech Recognition Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-14T10:34:38.492305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 07f4ac59-031e-49c0-91d6-d3d7ecfff20c · outbound

This paper cites Two-Pass End-to-End Speech Recognition.

Two-Pass End-to-End Speech Recognition Two-Pass End-to-End Speech Recognition

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:37.819273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e4112fc-77d2-4743-8963-47173b0159da · outbound

This paper cites Deep ﬁnetuning.

Two-Pass End-to-End Speech Recognition Deep ﬁnetuning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.447444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c8dfa28d-7db3-4d05-87e5-1c7d997baf67 · outbound

This paper cites an unresolved cited work.

Two-Pass End-to-End Speech Recognition Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-14T10:34:38.469298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 46b64c6e-b971-4989-8e51-b2657a3fc8e1 · outbound

This paper cites an unresolved cited work.

Two-Pass End-to-End Speech Recognition Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-14T10:34:38.458638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 18024fc8-b5aa-4a0a-ab7f-798a2880506f · outbound

This paper cites Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer,.

Two-Pass End-to-End Speech Recognition Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.331886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d2313ea3-0b2f-472b-8098-87607c33b2b1 · outbound

This paper cites Data Sets Our experiments are conducted on a ∼30,000 hour training set consisting of 43 million English utterances.

Two-Pass End-to-End Speech Recognition Data Sets Our experiments are conducted on a ∼30,000 hour training set consisting of 43 million English utterances

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.435727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aa66253f-7f23-4006-abfa-46d4b7e07dc9 · outbound

This paper cites Joint CTC-attention based end-to-end speech recognition using multi-task learning,.

Two-Pass End-to-End Speech Recognition Joint CTC-attention based end-to-end speech recognition using multi-task learning,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.320204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bd413fae-eeb4-4a9c-a524-9344b812c85d · outbound

This paper cites side-by-side.

Two-Pass End-to-End Speech Recognition side-by-side

Reference 9

Resolution: malformed identifier; raw_fallback, observed 2026-08-14T10:34:38.409874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 104cc18e-8ef7-4532-a6c2-d47953c7e2cd · outbound

This paper cites Speciﬁcally, we use a second-pass LAS decoder to rescore hypotheses from a ﬁrst-pass RNN-T system.

Two-Pass End-to-End Speech Recognition Speciﬁcally, we use a second-pass LAS decoder to rescore hypotheses from a ﬁrst-pass RNN-T system

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.398335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9708761c-f828-481e-942b-fcf0321ec813 · outbound

This paper cites Recently, we presented a RNN-T E2E model that satisﬁes these constraints [1].

Two-Pass End-to-End Speech Recognition Recently, we presented a RNN-T E2E model that satisﬁes these constraints [1]

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.480781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c8530e04-62fe-41cb-981e-a5c0130fae34 · outbound

This paper cites Streaming End-to-end Speech Recog- nition For Mobile Devices,.

Two-Pass End-to-End Speech Recognition Streaming End-to-end Speech Recog- nition For Mobile Devices,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.382289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2f991d48-56a0-4501-b707-c3f71afe1fff · outbound

This paper cites Lower frame rate neural network acoustic models,.

Two-Pass End-to-End Speech Recognition Lower frame rate neural network acoustic models,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.369528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 966a13d0-e2e5-4a06-812f-349743e2577c · outbound

This paper cites State-of-the-art speech recognition with sequence-to-sequence models,.

Two-Pass End-to-End Speech Recognition State-of-the-art speech recognition with sequence-to-sequence models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.357505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1aa3decf-b2aa-472f-9795-474245f625d8 · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Two-Pass End-to-End Speech Recognition Sequence Transduction with Recurrent Neural Networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:37.871036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3970e48-6866-4581-bd51-91c962f4f2ee · outbound

This paper cites Speech recognition with deep neural networks,.

Two-Pass End-to-End Speech Recognition Speech recognition with deep neural networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.344557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bd56e8e4-e5b7-4071-ba58-22ffc2120c10 · outbound

This paper cites Listen, Attend and Spell.

Two-Pass End-to-End Speech Recognition Listen, Attend and Spell

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:37.884102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf0d787a-4bf3-409e-b1cd-fe0b2741a7aa · outbound

This paper cites An analysis of.

Two-Pass End-to-End Speech Recognition An analysis of

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.197824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 92b0d931-7527-4e0f-85da-ab84b7ed25ea · outbound

This paper cites Monotonic chunkwise alignments,.

Two-Pass End-to-End Speech Recognition Monotonic chunkwise alignments,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.309165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e42ad640-6261-4769-9d9c-45faf0124ae0 · outbound

This paper cites Personalized speech recognition on mobile devices,.

Two-Pass End-to-End Speech Recognition Personalized speech recognition on mobile devices,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.296736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9b217947-7f0c-416a-96d4-3903f5b11c3e · outbound

This paper cites Bringing contextual information to Google speech recognition,.

Two-Pass End-to-End Speech Recognition Bringing contextual information to Google speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.281352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f0e5263f-58bf-4e5e-858c-4788da92304a · outbound

This paper cites A word graph algorithm for large vocabulary continuous speech recognition,.

Two-Pass End-to-End Speech Recognition A word graph algorithm for large vocabulary continuous speech recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.268794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 849f91b8-e027-4fdb-8e87-19aeeaf52fb6 · outbound

This paper cites A comparison of several approximate algorithms for ﬁnding multiple (N-best) sentence hypotheses,.

Two-Pass End-to-End Speech Recognition A comparison of several approximate algorithms for ﬁnding multiple (N-best) sentence hypotheses,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.257629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 083df698-3a9d-4311-9481-0e6653a3639e · outbound

This paper cites From Feedforward to Recurrent LSTM Neural Networks for Language Models,.

Two-Pass End-to-End Speech Recognition From Feedforward to Recurrent LSTM Neural Networks for Language Models,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.246261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 454fbb18-7a89-43a2-b236-6130281078f0 · outbound

This paper cites Two Efﬁcient Lattice Rescoring Methods Using Recurrent Neural Network Language Models,.

Two-Pass End-to-End Speech Recognition Two Efﬁcient Lattice Rescoring Methods Using Recurrent Neural Network Language Models,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.234867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 15cc986e-69c3-4aed-9073-10cd37e31399 · outbound

This paper cites an unresolved cited work.

Two-Pass End-to-End Speech Recognition Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-14T10:34:38.422069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dd593bb3-5553-4b72-ba64-cfb31e97ddc9 · outbound

This paper cites Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition,.

Two-Pass End-to-End Speech Recognition Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.223434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 04b4557e-f7a2-4a9b-931f-d4f349661112 · outbound

This paper cites An analysis of incorporating an external language model into a sequence-to-sequence model,.

Two-Pass End-to-End Speech Recognition An analysis of incorporating an external language model into a sequence-to-sequence model,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.210161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 84e46858-4543-4a59-95c8-360bcee47ccd · outbound

This paper cites Attention-Based Models for Speech Recognition,.

Two-Pass End-to-End Speech Recognition Attention-Based Models for Speech Recognition,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.185636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9886bb4b-2671-4601-a786-6ab6a32def12 · outbound

This paper cites Minimum Word Error Rate Training for Attention-based Sequence-to-sequence Models,.

Two-Pass End-to-End Speech Recognition Minimum Word Error Rate Training for Attention-based Sequence-to-sequence Models,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.173470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a9daf532-0138-4bc9-9574-e6d0a4fde714 · outbound

This paper cites an unresolved cited work.

Two-Pass End-to-End Speech Recognition Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-14T10:34:38.158294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 80a38cfe-6b3f-497c-85c3-877e4d2d24bf · outbound

This paper cites Response time in man-computer conversational transactions,.

Two-Pass End-to-End Speech Recognition Response time in man-computer conversational transactions,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.142276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation eec20f37-0462-4104-8dee-e4beedfdacd6 · outbound

This paper cites Towards Better Decoding and Language Model Integration in Sequence to Sequence Models,.

Two-Pass End-to-End Speech Recognition Towards Better Decoding and Language Model Integration in Sequence to Sequence Models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.128438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f00f6b6e-4427-4da3-b6e9-170ddb215b2b · outbound

This paper cites Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-ﬁeld speech recognition in Google Home,.

Two-Pass End-to-End Speech Recognition Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-ﬁeld speech recognition in Google Home,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.115222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5c1b45be-d2aa-4e25-a4a3-839ca2404fa7 · outbound

This paper cites Recent Advances in Google Real-time HMM-driven Unit Selection Synthesizer,.

Two-Pass End-to-End Speech Recognition Recent Advances in Google Real-time HMM-driven Unit Selection Synthesizer,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.102545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c89cd9bf-b6df-4d15-8ae3-73a667f05167 · outbound

This paper cites Deep Context: End-to-End Contextual Speech Recognition,.

Two-Pass End-to-End Speech Recognition Deep Context: End-to-End Contextual Speech Recognition,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.089994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6b4abc42-f17a-49dc-98f7-d73fee6d7080 · outbound

This paper cites Attention Is All You Need.

Two-Pass End-to-End Speech Recognition Attention Is All You Need

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:37.963846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82af0a87-eeb4-4577-b162-d841e9636cdf · outbound

This paper cites Japanese and Korean voice search,.

Two-Pass End-to-End Speech Recognition Japanese and Korean voice search,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.077489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 055ed845-721d-4068-843e-82b2962ee2a5 · outbound

This paper cites Tensorﬂow: Large-scale machine learn- ing on heterogeneous distributed systems,.

Two-Pass End-to-End Speech Recognition Tensorﬂow: Large-scale machine learn- ing on heterogeneous distributed systems,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-14T10:34:37.972031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7128024-7ee7-4209-9b11-3970eead3c82 · outbound

This paper cites Lingvo: a modular and scalable framework for sequence- to-sequence modeling,.

Two-Pass End-to-End Speech Recognition Lingvo: a modular and scalable framework for sequence- to-sequence modeling,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T10:34:38.057464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 07f4ac59-031e-49c0-91d6-d3d7ecfff20c · inbound