Paper Citation Record · LEDGER

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech

As of 19 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2607.06054.

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

pith.paper-citation-record.v1
2607.06054 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-08T18:09:22.207379Z

measured 35 of 35 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 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

35 of 35 outbound references displayed

verified exact14
verified fuzzy19
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ea39cef1-c124-444d-ae96-bf6d446adb3d · outbound

This paper cites Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.812754Z

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 0627bc6e-6b43-49e5-8862-89b87b2d5768 · outbound

This paper cites Seed-TTS: A Family of High-Quality Versatile Speech Generation Models.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.411426Z

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 b412697a-b251-4b4a-b94f-6f3556a123e7 · outbound

This paper cites F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.418131Z

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 d91f1d7c-f71b-4933-a491-b1a8acb141e7 · outbound

This paper cites V oxcpm: Tokenizer-free tts for context-aware speech generation and true-to-life voice cloning.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech V oxcpm: Tokenizer-free tts for context-aware speech generation and true-to-life voice cloning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-08T18:15:21.414730Z

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 4c1970c9-3e0b-4d4c-a020-45df1c894965 · outbound

This paper cites Neural machine translation of rare words with subword units,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Neural machine translation of rare words with subword units,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.811016Z

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 7538783f-7645-4b28-aa03-4cb797798729 · outbound

This paper cites How good is your tokenizer? on the monolingual performance of multilingual language models,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech How good is your tokenizer? on the monolingual performance of multilingual language models,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.809133Z

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 1440e7c6-79ac-455e-aca8-1b12e7b7fc7e · outbound

This paper cites TAIDE-14-tasks,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech TAIDE-14-tasks,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.807521Z

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 5f02f3dd-7ab0-49d8-bc59-503a2115b820 · outbound

This paper cites Subword regularization: Improving neural network translation models with multiple subword candidates,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Subword regularization: Improving neural network translation models with multiple subword candidates,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.805639Z

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 47a616a0-07b8-4601-bc17-eceb86de30be · outbound

This paper cites SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.803922Z

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 69dc57fc-17b1-472d-acdd-45d4b33b2e1a · outbound

This paper cites Language models are unsupervised multitask learners,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Language models are unsupervised multitask learners,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.802149Z

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 2cdf9f82-fe6b-4f96-aabf-ff02d1741d94 · outbound

This paper cites The Llama 3 Herd of Models.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech The Llama 3 Herd of Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.408170Z

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 7d1d33ce-b132-46c3-a717-5bd5d241cf15 · outbound

This paper cites Qwen2.5 Technical Report.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Qwen2.5 Technical Report

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.420625Z

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 dfcf7a62-00a4-4f76-b8b8-e3f1d791c255 · outbound

This paper cites Gemma 3 Technical Report.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Gemma 3 Technical Report

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.405036Z

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 2cb84713-9bfe-408b-aa21-f21b4dcd27b1 · outbound

This paper cites Language model tokenizers introduce unfairness between languages,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Language model tokenizers introduce unfairness between languages,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.799385Z

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 da46738a-c53f-4d58-895d-03b5cb3b24ac · outbound

This paper cites Do all languages cost the same? tokenization in the era of commercial language models,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Do all languages cost the same? tokenization in the era of commercial language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.797728Z

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 3b210c8d-18a7-4b76-b9f5-247523a5f271 · outbound

This paper cites Tokenization and the noiseless channel,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Tokenization and the noiseless channel,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.795843Z

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 fa479ae6-6507-4e3a-b99f-df5a05da8949 · outbound

This paper cites ByT5: Towards a token-free future with pre-trained byte-to-byte models,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech ByT5: Towards a token-free future with pre-trained byte-to-byte models,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.794079Z

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 683accf1-75f2-479e-a31f-9ea262f90d1f · outbound

This paper cites CANINE: Pre- training an efficient tokenization-free encoder for language representation,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech CANINE: Pre- training an efficient tokenization-free encoder for language representation,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.792454Z

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 f7a07615-782c-46cf-9705-ed68883be3d2 · outbound

This paper cites Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.790629Z

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 6fa43e09-9a85-4bbf-9982-bcb5baabf37d · outbound

This paper cites FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.402116Z

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 de215d58-4d20-431c-b6a0-5abd1419cfa9 · outbound

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

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.448138Z

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 211628dd-e43b-4b96-b8ea-8145568cbe2c · outbound

This paper cites VoxCPM2 Technical Report.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech VoxCPM2 Technical Report

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.444610Z

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 e7758f09-b868-4f3e-a232-1f9dd80f55e6 · outbound

This paper cites XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.442023Z

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 f8d9d8f1-7139-430b-af31-c6725f1fad10 · outbound

This paper cites End-to-end code- switching TTS with cross-lingual language model,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech End-to-end code- switching TTS with cross-lingual language model,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.823325Z

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 fca8eed3-3b5b-49cc-b35d-de97e0fc9390 · outbound

This paper cites wav2vec 2.0: A framework for self-supervised learning of speech representations,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.821704Z

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 979ee19d-444e-42b1-86d6-a281b7ac3e86 · outbound

This paper cites HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.819958Z

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 9c87759f-c7a2-407e-9837-2d744114017e · outbound

This paper cites Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T18:15:21.438746Z

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 a16b8910-8d6b-4820-8a3b-83ab76d55271 · outbound

This paper cites Measuring Taiwanese Mandarin Language Understanding.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Measuring Taiwanese Mandarin Language Understanding

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.435702Z

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 40bfac51-d6fb-42a3-9f54-3faa9e183317 · outbound

This paper cites A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T18:15:21.432691Z

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 ef006d06-41bf-4e44-924d-55f054600b60 · outbound

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

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Robust speech recognition via large-scale weak supervision,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.818325Z

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 2a8c4b16-c5d3-482c-90a1-5aaa4ca3198d · outbound

This paper cites TAIDE: Trustworthy AI dialogue engine,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech TAIDE: Trustworthy AI dialogue engine,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.816380Z

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 08e8e8ea-648a-49cc-8ec2-721d88f5541e · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.429411Z

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 4631df5b-9a73-4345-aef7-d27a01329265 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.426548Z

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 fe9107d5-cc52-41bc-9000-ac771acf71a7 · outbound

This paper cites GQA: Training generalized multi-query transformer models from multi-head checkpoints,.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech GQA: Training generalized multi-query transformer models from multi-head checkpoints,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T18:15:21.814709Z

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 2f3e2db9-eab4-4975-b266-fb4c20b91f94 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-08T18:15:21.423524Z

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

No inbound Pith citation observations are available.