Paper Citation Record · LEDGER

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition

As of 15 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.14973.

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

pith.paper-citation-record.v1
2506.14973 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:15:35.534745Z

measured 43 of 43 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 2026-08-07T00:15:31.637991Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T00:15:36.638294Z

Reference resolution

42 of 42 outbound references displayed

verified exact3
verified fuzzy25
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1cb698a3-00fe-4f98-b35f-911e14d81859 · outbound

This paper cites Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T00:15:36.767510Z

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 50e11f99-4d16-4569-beff-41f8e773917f · outbound

This paper cites Multi-channel Speech Large Language Model Our training of multi-channel SLLM builds on recent approach that integrate speech capabilities into LLMs via audio encoders [6,7].

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Multi-channel Speech Large Language Model Our training of multi-channel SLLM builds on recent approach that integrate speech capabilities into LLMs via audio encoders [6,7]

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.248025Z

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 fb20a46a-9dda-4040-977d-8ddecbbb1fc8 · outbound

This paper cites The linear projection layer, inserted before the audio encoder, plays a crucial role in highlighting rel- evant information from different channels.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition The linear projection layer, inserted before the audio encoder, plays a crucial role in highlighting rel- evant information from different channels

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.237543Z

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 c591ff3e-7561-41dc-8f4f-315eec63794a · outbound

This paper cites what is said from where?.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition what is said from where?

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.225515Z

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 bb2995a2-50ce-4363-87ad-e3011940a432 · outbound

This paper cites Room impulse responses (RIRs) from real environments are used to model spatial diver- sity, generating 12 distinct directions at 30° resolution.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Room impulse responses (RIRs) from real environments are used to model spatial diver- sity, generating 12 distinct directions at 30° resolution

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.215265Z

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 15a52cad-7e59-40c2-b47a-c169233a8b01 · outbound

This paper cites We propose two key techniques to infuse directional knowledge: serialized directional output training (S-DOT) and contrastive direction data augmentation (CDDA).

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition We propose two key techniques to infuse directional knowledge: serialized directional output training (S-DOT) and contrastive direction data augmentation (CDDA)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.204153Z

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 5b10a140-ff96-45eb-85c7-17f2229eecec · outbound

This paper cites The Llama 3 Herd of Models.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:32.388916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56dd6d6f-3888-4ced-ad1f-c4cebc8ed60f · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:32.596278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8325d0f-97bb-40d7-a816-2a9df751ad3b · outbound

This paper cites Flamingo: a visual language model for few-shot learning,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Flamingo: a visual language model for few-shot learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.184198Z

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 4f54d92f-7020-4eea-b640-2f31990c8bad · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.173990Z

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 da6c1df5-b888-478a-a255-ece4e2b54297 · outbound

This paper cites Listen, Think, and Understand.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Listen, Think, and Understand

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.044745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38f7772e-a80c-470e-b9a1-6a7f69c7302a · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.154751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7e93bf-5eb8-43e9-b9a6-55750feeaa97 · outbound

This paper cites Prompt- ing large language models with speech recognition abilities,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Prompt- ing large language models with speech recognition abilities,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.164049Z

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 4a17e89e-1ff1-4317-84f3-7f7f2abdfd49 · outbound

This paper cites On decoder-only architecture for speech- to-text and large language model integration,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition On decoder-only architecture for speech- to-text and large language model integration,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.402493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba36f91-7c00-45e0-8d8b-5dd98e62360c · outbound

This paper cites DiarizationLM: Speaker Diarization Post-Processing with Large Language Models.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition DiarizationLM: Speaker Diarization Post-Processing with Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.511719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01323e4e-b7f6-401b-b0e0-80cdde10a410 · outbound

This paper cites Enhancing speaker diarization with large language models: A contextual beam search approach,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Enhancing speaker diarization with large language models: A contextual beam search approach,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.140431Z

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 0e339b61-9b3f-41ca-b9c8-68f7e852692c · outbound

This paper cites SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.745532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae76af26-db9a-431e-91ec-fd57123a4bdf · outbound

This paper cites Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:33.903012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f9a1f53-f4e5-4fec-8133-2537b80faf4d · outbound

This paper cites A consolidated perspective on multimicrophone speech enhance- ment and source separation,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition A consolidated perspective on multimicrophone speech enhance- ment and source separation,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.126518Z

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 71860510-eea6-4232-9f90-e2b47f8e5002 · outbound

This paper cites Brandstein and D.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Brandstein and D

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.115657Z

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 47d13b95-e54d-4271-95bd-f1254597a91e · outbound

This paper cites Zotter and M.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Zotter and M

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.095902Z

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 3ce9e89e-389f-4100-8770-0ffc268262a2 · outbound

This paper cites Microphone arrays,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Microphone arrays,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.077048Z

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 b9c3ccde-d41b-4734-a612-e545a2a8e62b · outbound

This paper cites Superdirectional microphone arrays,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Superdirectional microphone arrays,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.053546Z

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 12b1c040-f580-404d-bec9-3f57041fdb38 · outbound

This paper cites Deep beamforming networks for multi-channel speech recognition,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Deep beamforming networks for multi-channel speech recognition,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:39.009949Z

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 b974f605-8e6f-4f6d-9c71-29b1c273ea28 · outbound

This paper cites Probabilistic spa- tial dictionary based online adaptive beamforming for meeting recognition in noisy and reverberant environments,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Probabilistic spa- tial dictionary based online adaptive beamforming for meeting recognition in noisy and reverberant environments,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.986803Z

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 6b8bc205-daff-4162-a275-93c90d715fed · outbound

This paper cites Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:36.387995Z

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 31854048-be1d-4b0f-b6ff-ebb21eaab68d · outbound

This paper cites Directional speech recognition for speaker disambiguation and cross-talk suppression,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Directional speech recognition for speaker disambiguation and cross-talk suppression,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.968731Z

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 3e603ac7-2b99-47fa-80d3-fff4c023ac52 · outbound

This paper cites Directional Source Separation for Robust Speech Recognition on Smart Glasses.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Directional Source Separation for Robust Speech Recognition on Smart Glasses

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:36.114932Z

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 48845ac0-023b-46e7-8b35-6d3d50191440 · outbound

This paper cites Enhancing end-to-end multi-channel speech separation via spatial feature learning,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Enhancing end-to-end multi-channel speech separation via spatial feature learning,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.947158Z

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 ee99d47c-a641-4d19-85b4-903c31e9fffa · outbound

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

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Mimo-speech: End-to-end multi-channel multi-speaker speech recognition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.756170Z

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 a1985a62-bd9e-4738-a26f-b5ad12b8cab5 · outbound

This paper cites Neural target speech extraction: An overview,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Neural target speech extraction: An overview,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:34.554749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535f180e-af2b-4c86-b58b-b85bc8ddf28d · outbound

This paper cites BAT: Learning to Reason about Spatial Sounds with Large Language Models.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition BAT: Learning to Reason about Spatial Sounds with Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:34.589561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07974889-09e9-4dca-ba57-b5ebdcd56858 · outbound

This paper cites Can Large Language Models Understand Spatial Audio?.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Can Large Language Models Understand Spatial Audio?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:34.635035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3574386-e408-4bea-8dce-8269fad04817 · outbound

This paper cites Teleconference application and b-format microphone array for directional audio coding,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Teleconference application and b-format microphone array for directional audio coding,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.436430Z

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 06288c03-cb96-480f-90b2-d299b56ac390 · outbound

This paper cites Agadir: Towards array-geometry agnostic direc- tional speech recognition,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Agadir: Towards array-geometry agnostic direc- tional speech recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:38.136109Z

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 a40baea8-9927-4ff6-b9a3-2bd36eb0a20e · outbound

This paper cites Attention is all you need,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Attention is all you need,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:34.856268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7dc434-8070-4b91-bcb5-7a33a907233a · outbound

This paper cites Serialized Output Training for End-to-End Overlapped Speech Recognition.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Serialized Output Training for End-to-End Overlapped Speech Recognition

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:15:35.844750Z

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 cb5befdf-20b5-43f9-bcd6-4f17ea54a192 · outbound

This paper cites Supervised contrastive learning,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Supervised contrastive learning,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:37.898018Z

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 a328c598-2467-4ce8-a5cc-32d34b5aae82 · outbound

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

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Robust speech recognition via large-scale weak su- pervision,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:37.626666Z

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 af3b3db4-609d-43a5-8c4f-2ee5a22968eb · outbound

This paper cites Project Aria: A New Tool for Egocentric Multi-Modal AI Research.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Project Aria: A New Tool for Egocentric Multi-Modal AI Research

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:35.232303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f95bb6b6-41ec-48d9-ac9d-8f4df2722ed4 · outbound

This paper cites Lib- rispeech: an asr corpus based on public domain audio books,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Lib- rispeech: an asr corpus based on public domain audio books,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:37.360530Z

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 7daee259-b54f-4b21-abd2-996543c29792 · outbound

This paper cites Au- diochatllama: Towards general-purpose speech abilities for llms,.

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition Au- diochatllama: Towards general-purpose speech abilities for llms,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:15:37.083079Z

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.

Pith citing papers

Observation 1cb698a3-00fe-4f98-b35f-911e14d81859 · inbound