Paper Citation Record · LEDGER

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference

As of 19 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 2 inbound Pith citation observations for arXiv:2508.05835.

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

pith.paper-citation-record.v1
2508.05835 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:10:56.287904Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:10:55.955561Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T15:37:06.833872Z

Reference resolution

40 of 40 outbound references displayed

verified exact4
verified fuzzy20
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation afbe7124-0d3e-4167-9392-d6f72758aec9 · outbound

This paper cites NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:55.955561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 950b9b12-3f78-41ed-b821-de60d59ddb26 · outbound

This paper cites The model consists of a fully convolutional generator network and three discriminators.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference The model consists of a fully convolutional generator network and three discriminators

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.685548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 00d527d4-1350-40fd-9c23-cfa6c288af9a · outbound

This paper cites Experiments setup To assess the performance of our codec in comparison to the LFSC and explore the effects of bitrate reduction, we adopted Koel-TTS [4], a SOTA LLM-based TTS model.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Experiments setup To assess the performance of our codec in comparison to the LFSC and explore the effects of bitrate reduction, we adopted Koel-TTS [4], a SOTA LLM-based TTS model

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.679227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1071ceec-89b6-4776-a3a9-4b234389f202 · outbound

This paper cites Ex- perimental results demonstrate that NanoCodec surpasses exist- ing approaches at the same bitrate, offering significantly higher intelligibility and speaker similarity.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Ex- perimental results demonstrate that NanoCodec surpasses exist- ing approaches at the same bitrate, offering significantly higher intelligibility and speaker similarity

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.672746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation da807057-629e-4b7a-94b7-262b0f5dec08 · outbound

This paper cites Apcodec: A neural audio codec with parallel amplitude and phase spectrum encoding and decoding,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Apcodec: A neural audio codec with parallel amplitude and phase spectrum encoding and decoding,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.194681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041a70a0-4a23-48a0-99ff-73da461ceeda · outbound

This paper cites Low frame-rate speech codec: a codec designed for fast high-quality speech llm training and in- ference,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Low frame-rate speech codec: a codec designed for fast high-quality speech llm training and in- ference,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.665414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cdd5867a-8a93-41d2-8127-0046701c044a · outbound

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

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.208858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb8e12ee-b1fe-442a-829c-e1dedd053d87 · outbound

This paper cites Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.211282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb2b600d-3793-4d62-885d-b5c9278f1c04 · outbound

This paper cites Textless direct speech-to-speech translation with discrete speech representation,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Textless direct speech-to-speech translation with discrete speech representation,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.658223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 382689a3-48e7-4480-a2a2-89ac25cc526a · outbound

This paper cites Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T23:10:56.411058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7dc6b11d-0f94-4ca5-ab33-6a4a53bb0b60 · outbound

This paper cites Soundstream: An end-to-end neural audio codec,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Soundstream: An end-to-end neural audio codec,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.220079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af937a02-c454-42b9-975e-0e3e05475f9b · outbound

This paper cites High Fidelity Neural Audio Compression.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference High Fidelity Neural Audio Compression

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.222307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f35b59-de99-4771-8b28-d71248dd34db · outbound

This paper cites Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.224674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98dd2d26-f5d8-442b-94b8-d74a8a45555b · outbound

This paper cites High-fidelity audio compression with improved rvqgan,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference High-fidelity audio compression with improved rvqgan,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.647619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b8db2c80-77b2-4d36-8c80-3fa3b8123f85 · outbound

This paper cites A review of vector quantization tech- niques,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference A review of vector quantization tech- niques,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.640927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d1a7139-afcd-4cd2-b250-22d6d087fde8 · outbound

This paper cites Gull: A Generative Multifunctional Audio Codec.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Gull: A Generative Multifunctional Audio Codec

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:10:56.388140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b73d46e2-9f29-439a-baa1-99d6ee3c5405 · outbound

This paper cites Finite Scalar Quantization: VQ-VAE Made Simple.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Finite Scalar Quantization: VQ-VAE Made Simple

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.233173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c4ada4-b184-455f-a5e6-262eccd6eb1a · outbound

This paper cites An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference An Intra-BRNN and GB-RVQ Based END-TO-END Neural Audio Codec

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:10:56.374626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6b674d29-0816-4322-a2d0-533578fbaf82 · outbound

This paper cites Lightcodec: A high fidelity neural audio codec with low computation complexity,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Lightcodec: A high fidelity neural audio codec with low computation complexity,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.634342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 512474a8-203f-478d-a365-a76c09d1c7a8 · outbound

This paper cites WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.240257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455d23af-0459-42ad-a8ba-04e35a6f588a · outbound

This paper cites Scaling Transformers for Low-Bitrate High-Quality Speech Coding.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Scaling Transformers for Low-Bitrate High-Quality Speech Coding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.242612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bf441b-e926-4c19-b4de-a6a7246a0672 · outbound

This paper cites TS3-Codec: Transformer-Based Simple Streaming Single Codec.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference TS3-Codec: Transformer-Based Simple Streaming Single Codec

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.245021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd81f46b-8c0e-4f37-a382-a856d0f0ee25 · outbound

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

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Moshi: a speech-text foundation model for real-time dialogue

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.247368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b9e15f-b0e8-4e70-bd45-72558da1b789 · outbound

This paper cites Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.627122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1df455ea-20ce-4795-9461-174ffa8818ab · outbound

This paper cites BigVGAN: A Universal Neural Vocoder with Large-Scale Training.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference BigVGAN: A Universal Neural Vocoder with Large-Scale Training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.252891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea94944-4489-48f0-ab34-9ca420020909 · outbound

This paper cites Neural networks fail to learn periodic functions and how to fix it,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Neural networks fail to learn periodic functions and how to fix it,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.620984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cea6704d-f41a-46f7-8b31-a4168a2226cd · outbound

This paper cites Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.614682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 912a39d0-ea31-4003-acb5-997a139fb7f2 · outbound

This paper cites Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:10:56.334788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9335ac55-5526-457e-9425-ac90053154d3 · outbound

This paper cites Common voice: A massively-multilingual speech corpus,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Common voice: A massively-multilingual speech corpus,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.607413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ff21f246-be34-40a2-b339-0ee3f54b5f07 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Adam: A Method for Stochastic Optimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.264700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4923fe-b2a9-459b-8a89-88c0e246b249 · outbound

This paper cites Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.601009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b090c511-9542-4e1e-a2e8-729a4a897822 · outbound

This paper cites Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:56.268724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 658ec4c7-6634-45e4-ac4e-9885b6aeb717 · outbound

This paper cites Scaling speech technology to 1,000+ languages,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Scaling speech technology to 1,000+ languages,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.590353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 22a2993b-9a5a-4372-af1a-dc1c1044f70f · outbound

This paper cites ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-05T23:10:56.312611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bb215012-18e3-4741-80c6-34cf59db1d03 · outbound

This paper cites Roach, A little encyclopaedia of phonetics.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Roach, A little encyclopaedia of phonetics

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.583466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0c728253-c6ff-47dd-a180-3c67174b4682 · outbound

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

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Libritts: A corpus derived from librispeech for text- to-speech,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.574765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3dd725f1-d2eb-469c-a2ba-3e2c21c24f34 · outbound

This paper cites Hi-Fi Multi-Speaker English TTS Dataset,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Hi-Fi Multi-Speaker English TTS Dataset,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.565836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5ee77d5e-84ef-498c-86ad-35a7632a363d · outbound

This paper cites Mls: A large-scale multilingual dataset for speech research,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Mls: A large-scale multilingual dataset for speech research,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.557346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 68de79d5-32d1-43a4-9482-35954a840aba · outbound

This paper cites Efficient sequence transduction by jointly predicting tokens and durations,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Efficient sequence transduction by jointly predicting tokens and durations,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.550562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a634319a-4e6c-45dd-bc1b-94800e445918 · outbound

This paper cites Titanet: Neural model for speaker representation with 1d depth-wise separable convo- lutions and global context,.

NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference Titanet: Neural model for speaker representation with 1d depth-wise separable convo- lutions and global context,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T23:10:56.542874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation afbe7124-0d3e-4167-9392-d6f72758aec9 · inbound