Paper Citation Record · LEDGER

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing

As of 7 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2506.03515.

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

pith.paper-citation-record.v1
2506.03515 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:07:16.011508Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:07:15.848160Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T11:07:16.177718Z

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy27
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 93fdb897-080f-4ebe-82f9-e6a9cf47d0ad · outbound

This paper cites With the advancement of these TTS models, they are increasingly being integrated into mobile applications, such as car navigation systems and conver- sational bots, among others.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing With the advancement of these TTS models, they are increasingly being integrated into mobile applications, such as car navigation systems and conver- sational bots, among others

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:17.294286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f18dc73-88da-4123-af45-e7050772b698 · outbound

This paper cites BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T11:07:16.183631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c190793b-cedf-4a57-aa83-31e17fa73b4d · outbound

This paper cites Experimental conditions We conducted experiments to evaluate the effectiveness of quantization in TTS and the proposed methods.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Experimental conditions We conducted experiments to evaluate the effectiveness of quantization in TTS and the proposed methods

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:17.233809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a02ebf19-4ce9-49e3-88f7-2d821f947136 · outbound

This paper cites Additionally, we introduced a method called weight indexing to further re- duce model size.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Additionally, we introduced a method called weight indexing to further re- duce model size

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:17.208813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8a8e447-a7ec-4f60-89d4-67d25a9e6042 · outbound

This paper cites Statistical parametric speech synthesis using deep neural networks,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Statistical parametric speech synthesis using deep neural networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:17.132185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 00cded20-c3d4-4e11-87c1-444357fbd23f · outbound

This paper cites A review of deep learning based speech synthesis,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A review of deep learning based speech synthesis,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:17.052148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be387944-fbb5-4f57-b581-8a029deb39bd · outbound

This paper cites A Survey on Neural Speech Synthesis.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A Survey on Neural Speech Synthesis

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.868253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2a5ed2-54ca-4500-9de1-dd48f9fc7aaf · outbound

This paper cites An overview of affective speech synthesis and conversion in the deep learning era,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing An overview of affective speech synthesis and conversion in the deep learning era,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.982845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1717cfa0-e933-462f-9bf0-49be3b888c6d · outbound

This paper cites A review of deep learning techniques for speech processing,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A review of deep learning techniques for speech processing,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.876798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff73a621-2552-4308-938e-0e2960bdff46 · outbound

This paper cites Lightspeech: Lightweight and fast text to speech with neural architecture search,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Lightspeech: Lightweight and fast text to speech with neural architecture search,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.920178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8ed470d-17de-4b6f-ba92-ff516a3754ab · outbound

This paper cites NIX- TTS: Lightweight and end-to-end text-to-speech via module-wise distillation,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing NIX- TTS: Lightweight and end-to-end text-to-speech via module-wise distillation,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.854393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a415607-475b-45f1-8746-f69a3fd4655a · outbound

This paper cites ConvNeXt-TTS and ConvNeXt-VC: ConvNeXt-based fast end-to-end sequence- to-sequence text-to-speech and voice conversion,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing ConvNeXt-TTS and ConvNeXt-VC: ConvNeXt-based fast end-to-end sequence- to-sequence text-to-speech and voice conversion,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.793431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation faec4f0e-4527-4b9f-ba91-ef103d5b4775 · outbound

This paper cites Lightweight and high-fidelity end-to-end text-to-speech with multi-band generation and inverse short-time fourier transform,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Lightweight and high-fidelity end-to-end text-to-speech with multi-band generation and inverse short-time fourier transform,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.712520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e63e2514-0b24-475b-84a1-56ea7d69b8c0 · outbound

This paper cites SpeedySpeech: Efficient neural speech synthesis,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing SpeedySpeech: Efficient neural speech synthesis,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.668543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8334b82f-376e-445c-8e6d-a9aab0b5ef3b · outbound

This paper cites ClariNet: Parallel wave genera- tion in end-to-end text-to-speech,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing ClariNet: Parallel wave genera- tion in end-to-end text-to-speech,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.519069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bd1b415c-6d0c-4b8b-98f8-cd73b22e992f · outbound

This paper cites Learning trans- ferable architectures for scalable image recognition,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Learning trans- ferable architectures for scalable image recognition,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.487361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0fd2d75a-7601-4844-9575-afb478bdf03e · outbound

This paper cites Neural architec- ture optimization,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Neural architec- ture optimization,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.458710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e365ab8a-b784-4406-927b-dea0195e3e40 · outbound

This paper cites A Survey of Quantization Methods for Efficient Neural Network Inference.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A Survey of Quantization Methods for Efficient Neural Network Inference

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.911425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66e34141-59a7-4542-98c8-f157e66ef0df · outbound

This paper cites A White Paper on Neural Network Quantization.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A White Paper on Neural Network Quantization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.915617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b73fbfdc-6eb7-47f8-997b-85e084ef77d8 · outbound

This paper cites Quantization and training of neural networks for efficient integer-arithmetic-only inference,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Quantization and training of neural networks for efficient integer-arithmetic-only inference,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.920093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8860598c-a142-46b9-b2e3-0ba8a37830e6 · outbound

This paper cites 4-bit conformer with native quantization aware training for speech recognition,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing 4-bit conformer with native quantization aware training for speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.422181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e1fb35f9-ac92-434d-a860-391eb6f714c5 · outbound

This paper cites Sub-8-bit quantization aware training for 8-bit neural network accelerator with on-device speech recog- nition,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Sub-8-bit quantization aware training for 8-bit neural network accelerator with on-device speech recog- nition,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.400339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b01f8e91-e75b-42df-9030-4c1bb95b2a43 · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.932038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84545911-dfa3-4c53-8391-f89bb49083ec · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.936246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca473a28-af43-4a51-b873-ce0797929651 · outbound

This paper cites Xnor- net: Imagenet classification using binary convolutional neural net- works,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Xnor- net: Imagenet classification using binary convolutional neural net- works,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.378017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 936962bc-4b6c-4a87-a362-e9eb04fa7182 · outbound

This paper cites Xnor-net++: Improved binary neural networks,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Xnor-net++: Improved binary neural networks,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.363698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d847e2c-0d6d-4c87-b603-f1474ac19363 · outbound

This paper cites Bi- nary neural networks: A survey,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Bi- nary neural networks: A survey,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.350061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 67157648-b8a5-4448-99fd-8055fc7b4463 · outbound

This paper cites Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.952081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5bd55e-4c7c-455f-85fb-f0a5a23aa082 · outbound

This paper cites Basic binary convolution unit for binarized image restoration network,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Basic binary convolution unit for binarized image restoration network,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.956304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0b1b8b5-a980-49dc-874e-1fb7a1824320 · outbound

This paper cites 2-bit conformer quantization for automatic speech recog- nition,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing 2-bit conformer quantization for automatic speech recog- nition,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.325105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1316b40f-bedc-464f-b6fb-aaaffeee4a0c · outbound

This paper cites Layer Normalization.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Layer Normalization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.964019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43d84c3-ccbe-47c0-b79a-d99ecc326002 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.968294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd45b6a-61db-44f3-a43d-6ae33f3a847e · outbound

This paper cites LibriTTS-R: A re- stored multi-speaker text-to-speech corpus,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing LibriTTS-R: A re- stored multi-speaker text-to-speech corpus,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.311000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3c061aa4-0e4d-4483-abff-bcc75e52e1a1 · outbound

This paper cites Montreal forced aligner: Trainable text-speech align- ment using kaldi.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Montreal forced aligner: Trainable text-speech align- ment using kaldi

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.976191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6d8f0d3-7416-4d71-9a2d-48f364840280 · outbound

This paper cites JETS: Jointly training FastSpeech2 and HiFi-GAN for end to end text to speech,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing JETS: Jointly training FastSpeech2 and HiFi-GAN for end to end text to speech,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.288337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3fbcff8e-7765-488c-9c19-77f52fb983a2 · outbound

This paper cites Attention is all you need,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Attention is all you need,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.274414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd81318d-60cb-4fc6-9aa7-6d153005d1be · outbound

This paper cites HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.988524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef1e13bf-870b-48e6-95e9-399534091eb8 · outbound

This paper cites Mixture density networks,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Mixture density networks,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.250799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 173f5761-5bf6-44ac-bb83-bed9835ba29e · outbound

This paper cites Phone-level prosody modelling with GMM- based MDN for diverse and controllable speech synthesis,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Phone-level prosody modelling with GMM- based MDN for diverse and controllable speech synthesis,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.236549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d6f607e7-86e4-42f1-85b7-7924bfe6a5fe · outbound

This paper cites Decoupled weight decay regulariza- tion,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Decoupled weight decay regulariza- tion,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:15.999816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66ccd60d-2f71-4b6a-8be3-0647b003832d · outbound

This paper cites An Exponential Learning Rate Schedule for Deep Learning.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing An Exponential Learning Rate Schedule for Deep Learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:16.003624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77ea45f8-2840-451b-9988-e33d945942d2 · outbound

This paper cites ESPnet-TTS: Uni- fied, reproducible, and integratable open source end-to-end text- to-speech toolkit,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing ESPnet-TTS: Uni- fied, reproducible, and integratable open source end-to-end text- to-speech toolkit,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.212447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 185acd47-4d21-42b7-9c1a-2d5c26d6f8d0 · outbound

This paper cites A method for the construction of minimum- redundancy codes,.

BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing A method for the construction of minimum- redundancy codes,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:07:16.198390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 1f18dc73-88da-4123-af45-e7050772b698 · inbound