Paper Citation Record · LEDGER

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding

As of 7 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2505.24820.

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

pith.paper-citation-record.v1
2505.24820 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:19:03.988835Z

measured 36 of 36 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 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

36 of 36 outbound references displayed

verified exact1
verified fuzzy25
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40a7845b-64aa-4b1a-8603-a10eba5bbd0e · outbound

This paper cites Small-footprint keyword spotting using deep neural networks,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Small-footprint keyword spotting using deep neural networks,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:10.692811Z

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 576125be-7efa-4db4-8869-dd5b0e5df1eb · outbound

This paper cites Multi-task learning and weighted cross-entropy for dnn-based keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Multi-task learning and weighted cross-entropy for dnn-based keyword spotting,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:00.707955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7dad51d-c728-4538-a5ee-825625d8bf66 · outbound

This paper cites Compressed time delay neural network for small-footprint keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Compressed time delay neural network for small-footprint keyword spotting,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:10.441790Z

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 6cb99265-851e-41f4-a5a0-83fbd8d41d1a · outbound

This paper cites Text adaptive detection for customizable keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Text adaptive detection for customizable keyword spotting,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:10.092117Z

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 74d6320e-f709-4ca0-9c40-b91baf56ed54 · outbound

This paper cites Text-aware speech separation for multi-talker keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Text-aware speech separation for multi-talker keyword spotting,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:09.790094Z

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 569e28d9-7201-4607-8b5b-f007d3cf46b8 · outbound

This paper cites MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:19:04.474772Z

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 7a5d9b57-681b-4a6e-a3a3-279362e9252e · outbound

This paper cites Self-attention transducers for end-to-end speech recognition,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Self-attention transducers for end-to-end speech recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:09.609371Z

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 9fa23c3d-4ec9-4e85-9680-74cd8537d232 · outbound

This paper cites Transformer-Transducer: End-to-End Speech Recognition with Self-Attention.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Transformer-Transducer: End-to-End Speech Recognition with Self-Attention

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:01.332106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d836ed7d-4221-4fda-804e-49be7a1750a3 · outbound

This paper cites Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:09.323308Z

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 f93c5290-5484-4848-bfae-31d685209850 · outbound

This paper cites ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:09.130396Z

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 4938cc31-fd36-4efe-a45b-5bfc1739ea9c · outbound

This paper cites Conformer: Convolution- augmented Transformer for Speech Recognition,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Conformer: Convolution- augmented Transformer for Speech Recognition,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:01.631171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f932803-aaed-4d1d-9318-ec47fabbddc3 · outbound

This paper cites Large-Scale Streaming End-to-End Speech Translation with Neural Transducers.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Large-Scale Streaming End-to-End Speech Translation with Neural Transducers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:01.722172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3208703-8afc-40fe-955b-7e983c385967 · outbound

This paper cites VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:01.847943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c9b7b9-8800-4463-83ba-73efb5daf17e · outbound

This paper cites Streaming small-footprint keyword spotting using sequence-to- sequence models,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Streaming small-footprint keyword spotting using sequence-to- sequence models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:08.897277Z

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 955f634b-17a6-4da2-85e4-6655b6afb25e · outbound

This paper cites Adaptation of rnn transducer with text-to-speech technology for keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Adaptation of rnn transducer with text-to-speech technology for keyword spotting,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:08.602495Z

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 060320cd-109c-4168-a2e5-6f70ffcbbf9b · outbound

This paper cites Improving rnn trans- ducer modeling for small-footprint keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Improving rnn trans- ducer modeling for small-footprint keyword spotting,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:08.297088Z

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 a7e195fb-519f-47fa-a25d-afad723fd7fc · outbound

This paper cites Rnn-t based open-vocabulary keyword spot- ting in mandarin with multi-level detection,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Rnn-t based open-vocabulary keyword spot- ting in mandarin with multi-level detection,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:08.105424Z

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 38930a02-9ed7-4c52-9fdd-40418d906bd4 · outbound

This paper cites CaTT- KWS: A multi-stage customized keyword spotting framework based on cascaded transducer-transformer,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding CaTT- KWS: A multi-stage customized keyword spotting framework based on cascaded transducer-transformer,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:07.575606Z

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 2e30d6a4-72d5-4839-a6a7-e55a806f1d32 · outbound

This paper cites TDT-KWS: fast and accurate keyword spotting using token-and-duration transducer,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding TDT-KWS: fast and accurate keyword spotting using token-and-duration transducer,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:06.854939Z

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 defb9deb-c112-421c-aa3e-54ec040b6b8f · outbound

This paper cites U2-KWS: unified two-pass open-vocabulary keyword spotting with keyword bias,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding U2-KWS: unified two-pass open-vocabulary keyword spotting with keyword bias,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:06.617608Z

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 cb096fb0-db40-4cec-b377-dbaba7eb3fdb · outbound

This paper cites Three-in-one: Fast and accurate transducer for hybrid-autoregressive speech recognition,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Three-in-one: Fast and accurate transducer for hybrid-autoregressive speech recognition,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:06.464267Z

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 d6220edf-908f-49eb-a7c8-8f8545d4d96b · outbound

This paper cites Nemo: a toolkit for building ai applications using neural modules,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Nemo: a toolkit for building ai applications using neural modules,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:06.315753Z

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 ab6c263f-ff78-493e-bd00-6c059a49176c · outbound

This paper cites Pruned rnn-t for fast, memory-efficient asr training,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Pruned rnn-t for fast, memory-efficient asr training,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:06.168334Z

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 a44eee6d-54a9-438d-a620-b1a68439ebc5 · outbound

This paper cites Rnn- transducer with stateless prediction network,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Rnn- transducer with stateless prediction network,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.948443Z

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 4624edf5-7ac1-4ac6-b6fe-47981f0307d7 · outbound

This paper cites Dropout: A simple way to prevent neural networks from overfitting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Dropout: A simple way to prevent neural networks from overfitting,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.757700Z

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 187f803c-8eb2-41c8-87f9-77179beee825 · outbound

This paper cites Efficient keyword spotting using dilated convolutions and gating,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Efficient keyword spotting using dilated convolutions and gating,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.589153Z

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 3e645d75-6a41-4a33-ab57-f553db2abeca · outbound

This paper cites Librispeech: an asr corpus based on public domain audio books,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Librispeech: an asr corpus based on public domain audio books,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.420708Z

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 e675afcc-afbe-408b-a6e4-59047e63509b · outbound

This paper cites AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:03.404914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19c52e71-435d-48de-9b53-4f838db885d1 · outbound

This paper cites Region proposal network based small-footprint keyword spotting,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Region proposal network based small-footprint keyword spotting,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:03.502345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baabb938-3dd2-4f70-b9b3-c8b61b396bb1 · outbound

This paper cites Audio augmentation for speech recognition.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Audio augmentation for speech recognition

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.230564Z

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 cdf56a29-64bf-4c38-9954-4a91d4efdc48 · outbound

This paper cites Specaugment: A simple data augmentation method for automatic speech recognition,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Specaugment: A simple data augmentation method for automatic speech recognition,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:05.040391Z

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 3843eb05-36e4-4313-9353-b6e23fd01e7a · outbound

This paper cites Deep-FSMN for large vocabulary continuous speech recognition,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Deep-FSMN for large vocabulary continuous speech recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:04.830444Z

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 5ec8b2d6-15be-4c00-a479-6c3fedea4a7d · outbound

This paper cites Learning pronunciation from a foreign language in speech synthesis networks.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Learning pronunciation from a foreign language in speech synthesis networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:03.795856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b49f958-28fc-4bec-9af8-3c9127c18d55 · outbound

This paper cites Adam: A method for stochastic optimiza- tion,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Adam: A method for stochastic optimiza- tion,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:03.881735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b692d8b1-6199-4619-a2b3-995820431b75 · outbound

This paper cites Decoupled weight decay regularization,.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding Decoupled weight decay regularization,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:19:04.653221Z

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 ba1f6b20-a679-4c40-94ab-177822983e7f · outbound

This paper cites VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech.

Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T12:19:01.968041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.