Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation | Paper Citation Record

Observation 300eb9ff-6fef-4fb1-b473-b40dd573e2f9 · outbound

This paper cites Recent advances in speech language models: A survey.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Recent advances in speech language models: A survey

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.871588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5fed312d-0459-4563-8504-e014a0f908ed · outbound

This paper cites On The Landscape of Spoken Language Models: A Comprehensive Survey.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation On The Landscape of Spoken Language Models: A Comprehensive Survey

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.883322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ff8859a0-4e56-439c-bd81-20434726eb29 · outbound

This paper cites Whislu: End-to-end spoken language under- standing with whisper,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Whislu: End-to-end spoken language under- standing with whisper,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.896735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0ea9fb9d-5818-477d-8733-3062002070c3 · outbound

This paper cites Adapting large language model with speech for fully formatted end- to-end speech recognition,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Adapting large language model with speech for fully formatted end- to-end speech recognition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.863174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 389a6a33-c15d-43d9-8cf5-abd64ccdf160 · outbound

This paper cites Speechgpt: Empowering large language models with intrinsic cross- modal conversational abilities.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Speechgpt: Empowering large language models with intrinsic cross- modal conversational abilities

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.874224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e81ae1d-a6f6-4baa-9178-f24eeb577039 · outbound

This paper cites Qwen2-Audio Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Qwen2-Audio Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.874065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0e0b2984-01f7-4fab-b5c3-ffcd1abad8e1 · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.877482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 93fe1a6b-ad6a-4f55-ad08-6aff920b25bc · outbound

This paper cites Understanding the modality gap: An empirical study on the speech-text alignment mechanism of large speech language models,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Understanding the modality gap: An empirical study on the speech-text alignment mechanism of large speech language models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.868810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c4d0555f-3f17-48b2-871e-541e176a93f1 · outbound

This paper cites Alignformer: Modality matching can achieve better zero-shot instruction-following speech-llm,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Alignformer: Modality matching can achieve better zero-shot instruction-following speech-llm,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.855242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f041ffa6-11a8-425f-af65-d53aae0d00bb · outbound

This paper cites Closing the gap between text and speech under- standing in llms.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Closing the gap between text and speech under- standing in llms

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.880630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 902335f4-2250-40f8-80a1-404cd4776d29 · outbound

This paper cites Speech discrete tokens or continuous features? a comparative analysis for spoken language understanding in speechllms,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Speech discrete tokens or continuous features? a comparative analysis for spoken language understanding in speechllms,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.851735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2f5244f6-835b-4b1b-aa46-d3a482c1ba55 · outbound

This paper cites Closing the Modality Reasoning Gap for Speech Large Language Models.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Closing the Modality Reasoning Gap for Speech Large Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.861469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 36f65776-7fda-4dcc-8e86-e7f4e60b5a83 · outbound

This paper cites E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.866228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a5a1814d-23ba-44b9-b394-ba3af7ed3611 · outbound

This paper cites Neural codec language models are zero-shot text to speech synthesizers.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Neural codec language models are zero-shot text to speech synthesizers

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.901398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c9232717-a8ce-44d3-b864-9e668f4e3b41 · outbound

This paper cites CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.867950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4ba1e5bb-777c-4576-960b-85610a148913 · outbound

This paper cites CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.854863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b5b13e28-7619-4746-90bf-68e753d28afd · outbound

This paper cites Pseudo-autoregressive neural codec language models for efficient zero-shot text-to-speech synthesis,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Pseudo-autoregressive neural codec language models for efficient zero-shot text-to-speech synthesis,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.889481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d599cbf4-104d-49dd-baff-0f6bad2c5390 · outbound

This paper cites Indextts2: A breakthrough in emotionally expressive and duration- controlled auto-regressive zero-shot text-to-speech,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Indextts2: A breakthrough in emotionally expressive and duration- controlled auto-regressive zero-shot text-to-speech,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.884335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 38a83d7b-9754-4a12-a95c-4ce473a84579 · outbound

This paper cites Fish audio s2 technical report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Fish audio s2 technical report

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.844200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7fa710d7-b84e-4d7a-a5e8-d77392b18b4e · outbound

This paper cites Zipvoice-dialog: Non-autoregressive spoken dialogue generation with flow matching,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Zipvoice-dialog: Non-autoregressive spoken dialogue generation with flow matching,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.887023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bb39d317-dfdd-4d0c-91ab-35088b251255 · outbound

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

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Moshi: a speech-text foundation model for real-time dialogue

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.840599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3cbc1c14-2319-4db7-a69a-b13171bb03a9 · outbound

This paper cites Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.847968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e39f0f1d-08dc-41f0-9592-42e850563044 · outbound

This paper cites Mimo-audio: Audio language models are few-shot learners.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Mimo-audio: Audio language models are few-shot learners

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.851849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4b757680-88ed-4970-a735-e69877b02bfa · outbound

This paper cites Kimi-Audio Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Kimi-Audio Technical Report

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.857825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f667b127-47d2-4a9e-9010-6a67b987b411 · outbound

This paper cites Slam-omni: Timbre-controllable voice interaction system with single-stage training,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Slam-omni: Timbre-controllable voice interaction system with single-stage training,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.879207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6284bc4d-a100-4ddd-a54e-bcf61a6de7ff · outbound

This paper cites Fun-audio-chat technical report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Fun-audio-chat technical report

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.864542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 72f844c2-04dc-4cec-9949-df97b3a813a5 · outbound

This paper cites MOSS-Audio Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation MOSS-Audio Technical Report

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.831036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dd8dc385-a372-410b-8289-a590a05290c1 · outbound

This paper cites GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.834436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b9d06f2e-9fcc-459b-87e8-153712bfeec4 · outbound

This paper cites LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.816779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1147bd70-7f4b-4557-a576-e455ba885218 · outbound

This paper cites Step-Audio 2 Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Step-Audio 2 Technical Report

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.819741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5a8cc085-5f67-4bc4-a36c-60adafae2633 · outbound

This paper cites Qwen2.5-Omni Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Qwen2.5-Omni Technical Report

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.809038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0f5caf8f-c1c8-4e9e-b8fe-ac27a14719bb · outbound

This paper cites Qwen3-Omni Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Qwen3-Omni Technical Report

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.805334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32763740-303e-4d41-870f-d964311c304e · outbound

This paper cites MinMo: A Multimodal Large Language Model for Seamless Voice Interaction.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation MinMo: A Multimodal Large Language Model for Seamless Voice Interaction

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T13:05:45.810988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 152cf258-b15f-43c8-81c8-60d6d204e8b2 · outbound

This paper cites Qwen3.5-Omni Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Qwen3.5-Omni Technical Report

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.788459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad9c68d7-5822-4c77-bd6e-dadc3a363a96 · outbound

This paper cites DeepSeek-V3 Technical Report.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation DeepSeek-V3 Technical Report

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.791055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a14c16ae-f3aa-48e1-bf3e-fc1ca63c2bde · outbound

This paper cites Better & faster large language models via multi-token prediction,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Better & faster large language models via multi-token prediction,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.881490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 646895cf-01a7-4a82-aa94-c4542d973006 · outbound

This paper cites Vita-audio: Fast interleaved cross-modal to- ken generation for efficient large speech-language model.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Vita-audio: Fast interleaved cross-modal to- ken generation for efficient large speech-language model

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.813181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ffef7a5f-8d1f-4a94-8c56-2abd76e49ffb · outbound

This paper cites V ocalnet: Speech llm with multi-token prediction for faster and high- quality generation,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation V ocalnet: Speech llm with multi-token prediction for faster and high- quality generation,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.894341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 284d6510-4b87-4449-8a25-cf50737a712c · outbound

This paper cites Similarity of neural network representations revisited.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Similarity of neural network representations revisited

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.904137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 54f3c543-76f8-4265-9022-990960a64bf8 · outbound

This paper cites Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Libriheavy: a 50,000 hours asr corpus with punctuation casing and context,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.891831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0a63bf1d-d401-45f8-b874-0cafc1f2d112 · outbound

This paper cites Covost 2 and massively multilingual speech translation,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Covost 2 and massively multilingual speech translation,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.899075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2a62a2a5-5f38-43e4-a3cf-359a9620df83 · outbound

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

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.823291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f53f3c67-8aba-40e1-9f0a-f97c394ae11f · outbound

This paper cites Towards efficient speech-text jointly decoding within one speech language model,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Towards efficient speech-text jointly decoding within one speech language model,

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.827711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d4fec4bf-a7f2-43ad-9246-5f7d04420371 · outbound

This paper cites Cvss corpus and massively multilingual speech-to-speech translation,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Cvss corpus and massively multilingual speech-to-speech translation,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.876551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4ef932e0-924c-4dc8-a955-0ffc0f0082a8 · outbound

This paper cites SLM-S2ST: A multimodal language model for direct speech- to-speech translation,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation SLM-S2ST: A multimodal language model for direct speech- to-speech translation,

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.793848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ac4e1bae-a699-4041-a37b-3006168c7580 · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.801831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b7ddd3d-8416-466c-891b-aad929053b09 · outbound

This paper cites Hello gpt-4o,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Hello gpt-4o,

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.906505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f7551b2a-e575-4830-96ee-99ca274072c9 · outbound

This paper cites Fleurs: Few-shot learning evaluation of universal representations of speech.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Fleurs: Few-shot learning evaluation of universal representations of speech

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.858208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4352eb73-d13b-46e8-9f44-9d7a586a73fb · outbound

This paper cites Ultraeval-audio: A unified framework for comprehensive evaluation of audio foundation models,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Ultraeval-audio: A unified framework for comprehensive evaluation of audio foundation models,

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.797735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a4ad798f-ee07-4c15-9f5d-1f73655c1a4f · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:05:45.837610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dbdb48ea-2166-4f36-8e38-5cf7a9447902 · outbound

This paper cites Vocalbench: Benchmarking the vocal conversational abilities for speech interaction models.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Vocalbench: Benchmarking the vocal conversational abilities for speech interaction models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-01T13:05:45.870823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation da0035ce-93ca-427e-bcaa-12191012280f · outbound

This paper cites Robust speech recognition via large-scale weak supervi- sion,.

Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation Robust speech recognition via large-scale weak supervi- sion,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-07-07T07:43:30.860708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers