Paper Citation Record · LEDGER

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios

As of 20 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 1 inbound Pith citation observation for arXiv:2506.14204.

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

pith.paper-citation-record.v1
2506.14204 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:25:14.088343Z

measured 40 of 40 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 2026-08-07T00:25:11.153732Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:25:14.576014Z

Reference resolution

39 of 39 outbound references displayed

verified exact1
verified fuzzy31
unresolved4
parse uncertain0
malformed identifier2
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 17609435-dd88-4d87-b18a-80565b52b05d · outbound

This paper cites However, the challenge of recognizing overlapping speech in multi-talker sce- narios remains a critical area of research.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios However, the challenge of recognizing overlapping speech in multi-talker sce- narios remains a critical area of research

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.432925Z

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.

Observation 6ac59759-3e08-4313-9f9c-91924f8bbea7 · outbound

This paper cites Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T00:25:14.796052Z

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.

Observation dc050b56-313c-4e70-9f5c-4ecdcaed6254 · outbound

This paper cites Avg. ” column. 0L and 0S are 0% overlap conditions with long and short inter-utterance silences. Column “CSS.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Avg. ” column. 0L and 0S are 0% overlap conditions with long and short inter-utterance silences. Column “CSS

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T00:25:19.413213Z

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.

Observation b0ae8375-f4be-4ed1-bb36-82e558f03bfd · outbound

This paper cites First, we leverage speech separated signals by using two channel CSS en- coder in our ASR models.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios First, we leverage speech separated signals by using two channel CSS en- coder in our ASR models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.394435Z

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.

Observation 374f03fc-4644-414b-99dd-684c65d1c9aa · outbound

This paper cites Clearly, this model significantly outperforms the CT-tSOT model in row 2 across all scenarios.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Clearly, this model significantly outperforms the CT-tSOT model in row 2 across all scenarios

Reference 5

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T00:25:19.403813Z

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.

Observation 094828e0-e881-4699-ae19-aed8ae57c985 · outbound

This paper cites Continuous speech separation: dataset and analysis,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Continuous speech separation: dataset and analysis,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.334387Z

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.

Observation ff11b036-779b-4206-a88c-99cf3cf7c00f · outbound

This paper cites Recent advances in end-to-end automatic speech recogni- tion,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Recent advances in end-to-end automatic speech recogni- tion,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.384937Z

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.

Observation 44ee7f40-c828-435e-9bfb-5a4d6a0507ba · outbound

This paper cites End-to-end speech recognition: A survey,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios End-to-end speech recognition: A survey,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:25:11.612090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53b917ff-5d68-4fbf-923e-7e8921d174ff · outbound

This paper cites A streaming on-device end-to-end model surpassing server-side conventional model quality and latency,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios A streaming on-device end-to-end model surpassing server-side conventional model quality and latency,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.369043Z

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.

Observation 90b34695-2ec8-4f44-9358-952d70846d45 · outbound

This paper cites Developing RNN- T models surpassing high-performance hybrid models with cus- tomization capability,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Developing RNN- T models surpassing high-performance hybrid models with cus- tomization capability,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.358880Z

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.

Observation 5c7c17db-7681-4857-9843-743497f39d4a · outbound

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

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Robust speech recognition via large-scale weak su- pervision,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.345872Z

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.

Observation 5dc1da24-8022-4cce-ab54-26ea26df6970 · outbound

This paper cites Streaming multi-talker ASR with token-level serialized output training,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Streaming multi-talker ASR with token-level serialized output training,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:18.351548Z

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.

Observation 58ea0287-25a2-4cd5-814e-4607eae42a51 · outbound

This paper cites Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.247621Z

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.

Observation 7641a0d2-6c85-49a2-999d-c6ebf8d76ca2 · outbound

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

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Permutation invari- ant training of deep models for speaker-independent multi-talker speech separation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.163355Z

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.

Observation b0b0ec89-5b07-4517-97c2-ee39ab7eba34 · outbound

This paper cites Recognizing multi-talker speech with permutation invariant training,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Recognizing multi-talker speech with permutation invariant training,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:18.836259Z

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.

Observation 7e7bfa55-b636-470b-a7dd-3e883a10abcd · outbound

This paper cites Figure 2:Conformer Transducer with Multi-Talker Cascaded Encoder.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Figure 2:Conformer Transducer with Multi-Talker Cascaded Encoder

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:19.422910Z

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.

Observation e4a1df3e-3b8a-40c8-8934-94486baaf80e · outbound

This paper cites Seri- alized output training for end-to-end overlapped speech recogni- tion,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Seri- alized output training for end-to-end overlapped speech recogni- tion,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:25:12.182783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d149a5-e6bb-4edc-9346-b6fcc1bf9619 · outbound

This paper cites Rec- ognizing overlapped speech in meetings: A multichannel separa- tion approach using neural networks,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Rec- ognizing overlapped speech in meetings: A multichannel separa- tion approach using neural networks,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:18.522978Z

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.

Observation 8821ce48-5924-452b-a494-017c7448fae0 · outbound

This paper cites Speech separation with large-scale self-supervised learning,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Speech separation with large-scale self-supervised learning,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:18.207138Z

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.

Observation 41310359-94db-4e23-b846-8f46bb6ac63a · outbound

This paper cites MIMO-Speech: End-to-end multi-channel multi-speaker speech recognition,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios MIMO-Speech: End-to-end multi-channel multi-speaker speech recognition,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:18.017941Z

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.

Observation 85eaf911-914c-4e36-bb23-f6e0a365c14f · outbound

This paper cites Directional ASR: A new paradigm for E2E multi-speaker speech recognition with source localization,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Directional ASR: A new paradigm for E2E multi-speaker speech recognition with source localization,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.836005Z

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.

Observation e831f744-112f-4105-a331-d4b0176edca2 · outbound

This paper cites VarArray meets t-SOT: Advancing the state of the art of stream- ing distant conversational speech recognition,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios VarArray meets t-SOT: Advancing the state of the art of stream- ing distant conversational speech recognition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.651858Z

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.

Observation dd45a35d-d79b-4119-9662-38c566091302 · outbound

This paper cites End-to-end multi-speaker speech recognition with transformer,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios End-to-end multi-speaker speech recognition with transformer,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.507989Z

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.

Observation bfd09a9b-d49e-4d32-b0fc-2a0fc3c8789a · outbound

This paper cites Conformer: Convolution-augmented transformer for speech recognition,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Conformer: Convolution-augmented transformer for speech recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.356621Z

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.

Observation bea94d92-8c63-4f02-8bbe-cdf215b9f84e · outbound

This paper cites Developing real-time streaming transformer transducer for speech recognition on large- scale dataset,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Developing real-time streaming transformer transducer for speech recognition on large- scale dataset,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.206613Z

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.

Observation f4629428-c691-4067-815c-3d959b1c824a · outbound

This paper cites End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:25:13.014632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a2c18b8-95df-4fc7-b461-51197c454355 · outbound

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

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:17.059275Z

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.

Observation 9de94e1e-ff3d-4423-8f1d-ff0cd18b7326 · outbound

This paper cites Cascaded encoders for unifying streaming and non-streaming ASR,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Cascaded encoders for unifying streaming and non-streaming ASR,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.876718Z

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.

Observation 4d5f32ed-e341-4bcd-ad64-e3fb68ca3c44 · outbound

This paper cites Continuous speech separation with con- former,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Continuous speech separation with con- former,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.694122Z

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.

Observation f92627fb-4000-42c5-9777-7f6a30fdff3a · outbound

This paper cites Joint speaker counting, speech recognition, and speaker identification for overlapped speech of any number of speakers,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Joint speaker counting, speech recognition, and speaker identification for overlapped speech of any number of speakers,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.500799Z

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.

Observation 9541bc28-c7a5-457c-8a7a-1aba80653a23 · outbound

This paper cites Investigation of end-to-end speaker-attributed ASR for continuous multi-talker recordings,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Investigation of end-to-end speaker-attributed ASR for continuous multi-talker recordings,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.341036Z

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.

Observation 09f0485f-d3e8-4147-9a37-7c038e489e56 · outbound

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

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Joint CTC-attention based end-to-end speech recognition using multi-task learning,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.189953Z

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.

Observation ced51003-9cca-423f-8e83-2fc40c78685b · outbound

This paper cites High-accuracy and low-latency speech recognition with two-head contextual layer trajectory LSTM model,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios High-accuracy and low-latency speech recognition with two-head contextual layer trajectory LSTM model,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:16.008079Z

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.

Observation 7d6260b2-bf6c-44c3-a4b4-21f3d1b4747d · outbound

This paper cites The AMI meeting corpus: A pre- announcement,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios The AMI meeting corpus: A pre- announcement,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:15.804992Z

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.

Observation 11d42dff-65b2-4f51-85a2-71cfa4df692c · outbound

This paper cites The ICSI meeting corpus,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios The ICSI meeting corpus,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:15.576909Z

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.

Observation b0e05795-c22a-42df-8950-ffe751988e63 · outbound

This paper cites The NIST Scoring Toolkit (SCTK),.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios The NIST Scoring Toolkit (SCTK),

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:15.339241Z

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.

Observation 6436fc04-8ad3-4c5d-92c3-d361bb3c3fac · outbound

This paper cites WavLM: Large-scale self- supervised pre-training for full stack speech processing,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios WavLM: Large-scale self- supervised pre-training for full stack speech processing,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:25:13.906564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2e3f95-6411-428b-8f0f-65808b4eae26 · outbound

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

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:25:14.387880Z

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.

Observation 520496b5-07e4-401c-adb4-f49cf4309d22 · outbound

This paper cites Improving wideband speech recognition using mixed-bandwidth training data in CD- DNN-HMM,.

Improving Practical Aspects of End-to-End Multi-Talker Speech Recognition for Online and Offline Scenarios Improving wideband speech recognition using mixed-bandwidth training data in CD- DNN-HMM,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:25:15.063030Z

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.

Pith citing papers

Observation 6ac59759-3e08-4313-9f9c-91924f8bbea7 · inbound