Paper Citation Record · LEDGER

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO

As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2607.27756.

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

pith.paper-citation-record.v1
2607.27756 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T01:56:16.007863Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 788b3f6c-4db0-4df3-bd2c-836e83fa7150 · outbound

This paper cites GPT-4o System Card,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO GPT-4o System Card,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:10.416778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9560a833-0e86-4a0c-ab01-bab6f584bcbf · outbound

This paper cites Moshi: a speech-text foundation model for real-time dialogue.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Moshi: a speech-text foundation model for real-time dialogue

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:10.528940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1153c227-50cf-4b9e-89d4-0338aa6350c9 · outbound

This paper cites Personaplex: V oice and role control for full duplex conversational speech models,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Personaplex: V oice and role control for full duplex conversational speech models,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:10.668140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e624201f-2ee7-4850-a6d0-590cfeb18e85 · outbound

This paper cites Qwen2.5-Omni Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Qwen2.5-Omni Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:10.827949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdea526e-90f8-425c-8698-6402185f0f7d · outbound

This paper cites Qwen3-Omni Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Qwen3-Omni Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:10.937839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69039bc1-eb5e-4a90-b17d-cd000c1e5a83 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.074176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00afae82-4b4e-4571-bcd0-fbd8ddfa345e · outbound

This paper cites Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.217841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e6763b9-2544-45e1-82ae-e2b4c8cbe348 · outbound

This paper cites LLaMA-Omni: Seamless Speech Interaction with Large Language Models.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO LLaMA-Omni: Seamless Speech Interaction with Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.344932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c84c9f-daa9-43a0-bb18-054a639450ad · outbound

This paper cites Qwen2-Audio Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Qwen2-Audio Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.504456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f3b444-9dcc-47d1-adb1-8860bdf40f52 · outbound

This paper cites Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.607296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853fd419-db93-4bc9-a2f8-5aa3d67b57ab · outbound

This paper cites Some experiments on the recognition of speech, with one and with two ears,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Some experiments on the recognition of speech, with one and with two ears,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.708738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f3ad423-b469-408b-8477-4966ba6f9131 · outbound

This paper cites The cocktail party problem: what is it? how can it be solved? and why should animal behaviorists study it?.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO The cocktail party problem: what is it? how can it be solved? and why should animal behaviorists study it?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:11.843244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55221ab-6ea2-4c20-bc9b-964280ef28dd · outbound

This paper cites Just ASR + LLM? a study on speech large language models’ ability to identify and understand speaker in spoken dialogue,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Just ASR + LLM? a study on speech large language models’ ability to identify and understand speaker in spoken dialogue,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.025784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96e98f15-bfea-43ce-955f-b0418946de49 · outbound

This paper cites Avmeme exam: A multimodal multilingual multicultural benchmark for llms’ contextual and cultural knowledge and thinking,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Avmeme exam: A multimodal multilingual multicultural benchmark for llms’ contextual and cultural knowledge and thinking,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.212161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e849d692-f02c-4dcb-b34b-cdadafa53b4d · outbound

This paper cites MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.264320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b535e89-b1aa-4c09-bd24-d92b16131d16 · outbound

This paper cites M3-slu: Evaluating speaker- attributed reasoning in multimodal large language models,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO M3-slu: Evaluating speaker- attributed reasoning in multimodal large language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.391103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a86a3fd3-8800-476b-a9e9-0bd5e4630dfc · outbound

This paper cites Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.513345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028a8f72-c847-4269-b3c0-590c0f7d91ac · outbound

This paper cites Full-duplex-bench v1. 5: Evaluating overlap handling for full-duplex speech models,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Full-duplex-bench v1. 5: Evaluating overlap handling for full-duplex speech models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.628782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a0378b2-c122-4747-bbde-d0362c82c417 · outbound

This paper cites V oiceFilter: Targeted voice separation by speaker-conditioned spectrogram masking,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO V oiceFilter: Targeted voice separation by speaker-conditioned spectrogram masking,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.788543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db2eec55-b872-4286-8d59-91c69257d43d · outbound

This paper cites Listen, chat, and remix: Text-guided soundscape remixing for enhanced auditory experience,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Listen, chat, and remix: Text-guided soundscape remixing for enhanced auditory experience,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:12.958206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ce8180-6ef9-460a-9ea3-20aaf2cabc5f · outbound

This paper cites Meanflow-tse: One-step generative target speaker extraction with mean flow,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Meanflow-tse: One-step generative target speaker extraction with mean flow,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.053366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e40c67-e0bc-406c-a7a7-292ac888e500 · outbound

This paper cites Auxiliary interference speaker loss for target-speaker speech recognition,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Auxiliary interference speaker loss for target-speaker speech recognition,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.218631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0be647-fc06-45a2-bd0f-82b140f1b894 · outbound

This paper cites End-to-end multi-speaker speech recognition using speaker embeddings and transfer learning,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO End-to-end multi-speaker speech recognition using speaker embeddings and transfer learning,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.368342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a13fbb-261c-4d05-b1de-a7f176bdab43 · outbound

This paper cites Conformer- based target-speaker automatic speech recognition for single-channel audio,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Conformer- based target-speaker automatic speech recognition for single-channel audio,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.501136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4ed2fd-706e-4a63-a44a-245fa8281854 · outbound

This paper cites AAD-LLM: Neural attention-driven auditory scene understanding,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO AAD-LLM: Neural attention-driven auditory scene understanding,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.641217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd308f0-ab70-4ee6-a978-9b24da0e7a4e · outbound

This paper cites Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.771206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb5b584b-f626-4d57-9d08-740ad6673e3d · outbound

This paper cites LibriMix: An Open-Source Dataset for Generalizable Speech Separation.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO LibriMix: An Open-Source Dataset for Generalizable Speech Separation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:13.878197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abbb6c8e-01d8-4b57-a69d-a5131f0dfa40 · outbound

This paper cites CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.046887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 372b49b6-6131-4442-87d6-0f3b4d26654b · outbound

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

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO The AMI meeting corpus: A pre-announcement,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.210808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e893e9-b2e7-4de0-8798-c424b85a8856 · outbound

This paper cites Speak or stay silent: Context-aware turn-taking in multi-party dialogue,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Speak or stay silent: Context-aware turn-taking in multi-party dialogue,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.318275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b73ee49-b7d7-48fc-a4cf-e3096c73c695 · outbound

This paper cites Demand: a collection of multi- channel recordings of acoustic noise in diverse environments,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Demand: a collection of multi- channel recordings of acoustic noise in diverse environments,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.440453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322c8393-bb2d-436e-82e8-f7a5aaf6ef24 · outbound

This paper cites Dailytalk: Spoken dialogue dataset for conversational text-to-speech,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Dailytalk: Spoken dialogue dataset for conversational text-to-speech,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.600689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d352b3c-bae2-405b-abd6-074198edb42e · outbound

This paper cites Gemini 3 Pro Model Card,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Gemini 3 Pro Model Card,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.764304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a9853d-7f3f-4647-89fb-32106e1f0d4e · outbound

This paper cites Qwen3-TTS Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Qwen3-TTS Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:14.899573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c8fe36-c9f4-459e-8653-00ee3bb37596 · outbound

This paper cites Libritts: A corpus derived from librispeech for text-to-speech,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Libritts: A corpus derived from librispeech for text-to-speech,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.055628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2746be07-1660-430e-9efe-098d854ecdbb · outbound

This paper cites Lora: Low-rank adaptation of large language models.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Lora: Low-rank adaptation of large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.219253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a143f9-fc06-49cd-a2f6-9738a33dd814 · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Llamafactory: Unified efficient fine-tuning of 100+ language models,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.367153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2247c9d4-d3f0-4796-a860-6908b53e6719 · outbound

This paper cites Swift: a scalable lightweight infrastructure for fine-tuning,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Swift: a scalable lightweight infrastructure for fine-tuning,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.428263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c80b2d73-dec6-4751-a870-8d5ae80c90d6 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Efficient memory management for large language model serving with pagedattention,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.516842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d816465-5b4d-4edf-9dae-ef9edcb73b9d · outbound

This paper cites Step-Audio 2 Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Step-Audio 2 Technical Report

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.582007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58d307b7-9d7c-404c-854a-5ea24074648e · outbound

This paper cites Kimi-Audio Technical Report.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Kimi-Audio Technical Report

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.643853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d578521b-6cf5-42c1-9e29-891972d52e35 · outbound

This paper cites METEOR: An automatic metric for MT evaluation with improved correlation with human judgments,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO METEOR: An automatic metric for MT evaluation with improved correlation with human judgments,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.710381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 439f410c-7174-4e76-9da5-854c20fb5d8f · outbound

This paper cites ROUGE: A package for automatic evaluation of summaries,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO ROUGE: A package for automatic evaluation of summaries,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.786819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6ba220-21d1-4e99-b018-4c3eff565498 · outbound

This paper cites Bertscore: Evaluating text generation with bert,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Bertscore: Evaluating text generation with bert,

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:15.898512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68fa27f4-268f-4a15-a670-90b7d39b72ba · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks,.

Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO Sentence-bert: Sentence embeddings using siamese bert-networks,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T01:56:16.007863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.