Paper Citation Record · LEDGER

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation

As of 21 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2505.03273.

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

pith.paper-citation-record.v1
2505.03273 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:00:56.905378Z

measured 45 of 45 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 2026-08-07T14:22:07.274041Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T14:22:07.706463Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy32
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb82f4bb-e837-44b9-aac6-b6af1798b9ea · outbound

This paper cites On synthesis for supervised monaural speech sepa- ration in time domain.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation On synthesis for supervised monaural speech sepa- ration in time domain

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.884092Z

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 d86f38fc-6e6a-4287-a6d9-140a4b3364ec · outbound

This paper cites w2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre- training.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation w2v-bert: Combining contrastive learning and masked language modeling for self-supervised speech pre- training

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.815273Z

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 36835ab7-18dd-4771-89f6-b7624a4786d6 · outbound

This paper cites Tokensplit: Using discrete speech rep- resentations for direct, refined, and transcript-conditioned speech separation and recognition.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Tokensplit: Using discrete speech rep- resentations for direct, refined, and transcript-conditioned speech separation and recognition

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.792167Z

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 50c3a8d8-b05b-4032-9768-aeca4ec52786 · outbound

This paper cites Prompting large language mod- els with speech recognition abilities.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Prompting large language mod- els with speech recognition abilities

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.763097Z

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 8e4f2403-fb44-4916-8f8b-4ff217f7725a · outbound

This paper cites Classifier-Free Diffusion Guidance.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Classifier-Free Diffusion Guidance

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.711748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9499b5ea-935f-4af4-8ff5-e1e43115f453 · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, et al.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Hu, Yelong Shen, Phillip Wallis, et al

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.696878Z

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 19b7d8bd-f906-4480-9d78-f6900f39fbef · outbound

This paper cites Listen again and choose the right answer: A new paradigm for automatic speech recognition with large lan- guage models.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Listen again and choose the right answer: A new paradigm for automatic speech recognition with large lan- guage models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.676691Z

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 db27073c-16e0-429e-ac79-1147475812fb · outbound

This paper cites Speak, read and prompt: High- fidelity text-to-speech with minimal supervision.Trans.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Speak, read and prompt: High- fidelity text-to-speech with minimal supervision.Trans

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.655603Z

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 538c74ae-c9f7-49ea-8077-8533f8cc8926 · outbound

This paper cites High-fidelity audio compression with improved RVQGAN.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation High-fidelity audio compression with improved RVQGAN

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.634439Z

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 bf5cf04e-ab6b-42b1-a614-b7f04546dc47 · outbound

This paper cites End-to-end speech recognition con- textualization with large language models.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation End-to-end speech recognition con- textualization with large language models

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.614448Z

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 24e27e22-4a97-4439-ac1c-40ec35a2581e · outbound

This paper cites Sparks of Large Audio Models: A Survey and Outlook.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Sparks of Large Audio Models: A Survey and Outlook

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.749176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 922cffed-6582-40d1-8fdc-be0c1d04fa64 · outbound

This paper cites A simultaneous denoising and dereverberation framework with target decoupling.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation A simultaneous denoising and dereverberation framework with target decoupling

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.593603Z

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 201c2e9c-47b7-4b8e-8844-8d1f8c80b6b9 · outbound

This paper cites Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation.IEEE ACM Trans.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation.IEEE ACM Trans

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.575857Z

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 1c58c0c4-3d1e-4c60-a53f-aae361cae874 · outbound

This paper cites Separate and diffuse: Using a pretrained diffusion model for better source separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Separate and diffuse: Using a pretrained diffusion model for better source separation

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.531540Z

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 3de85ac1-1770-48b3-8a45-fcdc59bcea21 · outbound

This paper cites Whamr!: Noisy and reverberant single-channel speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Whamr!: Noisy and reverberant single-channel speech separation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.511167Z

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 05a06c59-ad24-41af-916d-0cd341b9dab0 · outbound

This paper cites Separate in the speech chain: Cross-modal conditional audio-visual target speech extraction.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Separate in the speech chain: Cross-modal conditional audio-visual target speech extraction

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.489997Z

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 2dffa98c-4c8a-4e8f-b39e-d77e5abef56d · outbound

This paper cites Self-supervised disentangled representation learning for robust target speech extraction.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Self-supervised disentangled representation learning for robust target speech extraction

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.471894Z

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 5919b9f7-9363-4c0b-b1ac-dfe27aeb7334 · outbound

This paper cites To- wards real-time single-channel speech separation in noisy and reverberant environments.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation To- wards real-time single-channel speech separation in noisy and reverberant environments

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.453954Z

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 a6b90e55-e6b2-421b-ad7a-6bbfcd6c481f · outbound

This paper cites GPT-4 Technical Report.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation GPT-4 Technical Report

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.801363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea62bfca-26fc-420c-bb12-06c88b29c208 · outbound

This paper cites Librispeech: An ASR corpus based on public domain audio books.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Librispeech: An ASR corpus based on public domain audio books

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.435323Z

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 a016eddf-0e0c-4c1f-a8f9-b91c62a189f1 · outbound

This paper cites Whispering llama: A cross-modal generative error correction frame- work for speech recognition.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Whispering llama: A cross-modal generative error correction frame- work for speech recognition

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.399654Z

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 052bfd78-c4b2-4ac6-990a-9361d5c24e8e · outbound

This paper cites Reading to listen at the cocktail party: Multi-modal speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Reading to listen at the cocktail party: Multi-modal speech separation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.382734Z

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 e0a8286c-8f61-43c8-a11f-7e7d42539750 · outbound

This paper cites an unresolved cited work.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:00:57.366560Z

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 9dce4788-3367-44b8-9df6-d9a4bd8540af · outbound

This paper cites Diffusion-based generative speech source separa- tion.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Diffusion-based generative speech source separa- tion

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.348104Z

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 dc0d8819-6cd5-4ed1-8967-f5c5717f6a2d · outbound

This paper cites MUSAN: A Music, Speech, and Noise Corpus.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation MUSAN: A Music, Speech, and Noise Corpus

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.845561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb8d3e36-8890-4c85-8e09-97af7804af89 · outbound

This paper cites Attention is all you need in speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Attention is all you need in speech separation

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.328280Z

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 a51f2e1c-d105-4f1f-a45e-9f7cbcad5ff0 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation LLaMA: Open and Efficient Foundation Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.858665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34e9e1f0-9259-4a3f-8c28-7870a692af00 · outbound

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

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.866015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1d9dad0-c14d-4f8d-b20d-5efacb66d816 · outbound

This paper cites Noise-robust Speech Separation with Fast Generative Correction.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Noise-robust Speech Separation with Fast Generative Correction

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.871649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da8156d4-ecc8-44b2-a160-ff66a880bfa4 · outbound

This paper cites MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.877406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a74e3bf-9b48-4857-981e-f4ff71492af0 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Chain-of-thought prompting elicits reasoning in large language models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.307614Z

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 adf982fc-a6c8-42f4-8bf6-b8cdbb53a631 · outbound

This paper cites Wham!: Extending speech sepa- ration to noisy environments.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Wham!: Extending speech sepa- ration to noisy environments

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.288688Z

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 8a5e21d3-c3c8-4f83-bcd4-3d9801dd5214 · outbound

This paper cites Wavesplit: End-to-end speech separation by speaker clustering.IEEE ACM Trans.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Wavesplit: End-to-end speech separation by speaker clustering.IEEE ACM Trans

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.270319Z

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 7813718f-f81c-4666-9a96-ce3b9adefd72 · outbound

This paper cites Mossformer2: Combining transformer and rnn- free recurrent network for enhanced time-domain monau- ral speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Mossformer2: Combining transformer and rnn- free recurrent network for enhanced time-domain monau- ral speech separation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.249061Z

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 d85c08f4-b50e-4aa9-b33e-9cbfb75d2625 · outbound

This paper cites Neural target speech extraction: An overview.IEEE Signal Process.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Neural target speech extraction: An overview.IEEE Signal Process

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.228706Z

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 1bf192bc-e23c-49f7-bcb6-7723ee8b423c · outbound

This paper cites Hershey, Zhuo Chen, Jonathan Le Roux, and Shinji Watanabe.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Hershey, Zhuo Chen, Jonathan Le Roux, and Shinji Watanabe

Reference 2014

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.715769Z

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 e1852707-4c8c-4392-85ac-e2b9eeee2c82 · outbound

This paper cites Robust speech recognition via large-scale weak supervision.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Robust speech recognition via large-scale weak supervision

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.417283Z

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 a0c078dd-4811-49d3-b7a6-3839dcdf369a · outbound

This paper cites Diffusion-based signal refiner for speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Diffusion-based signal refiner for speech separation

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.704998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 304a15f9-76aa-4210-927a-79806076f873 · outbound

This paper cites Dual-path RNN: efficient long sequence model- ing for time-domain single-channel speech separation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Dual-path RNN: efficient long sequence model- ing for time-domain single-channel speech separation

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.551217Z

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 e0a20fec-036c-4818-bf47-a6526edf2e6d · outbound

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

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Wavlm: Large-scale self- supervised pre-training for full stack speech processing

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.862242Z

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 5722bfab-470e-4d5b-a8d8-f126a78667b0 · outbound

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

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation LibriMix: An Open-Source Dataset for Generalizable Speech Separation

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.674087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b47f20a1-140b-4e13-afcd-764dfc3fa142 · outbound

This paper cites Hyporadise: An open baseline for genera- tive speech recognition with large language models.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Hyporadise: An open baseline for genera- tive speech recognition with large language models

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.838144Z

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 9aa9bde5-d5c4-4086-9eaa-3ea72ed6151c · outbound

This paper cites SoundStorm: Efficient Parallel Audio Generation.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation SoundStorm: Efficient Parallel Audio Generation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T00:00:56.639061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19301482-3284-4bea-8927-84bc4cef4066 · outbound

This paper cites Multichannel audio database in var- ious acoustic environments.

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation Multichannel audio database in var- ious acoustic environments

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:00:57.740901Z

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 58f778a2-4cd6-4848-b207-4291a63e5542 · inbound

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline cites this paper.

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:22:07.710817Z

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.