Paper Citation Record · LEDGER

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions

As of 10 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2501.19377.

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

pith.paper-citation-record.v1
2501.19377 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:20:58.963820Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

38 of 38 outbound references displayed

verified exact2
verified fuzzy27
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9ad20b1c-eea4-4c56-bf5a-8e99c81bb305 · outbound

This paper cites V oice trigger system for Siri,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions V oice trigger system for Siri,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.515361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e722739-cb4b-4c7d-a7a1-bf045052f374 · outbound

This paper cites Efficient V oice Trigger Detection for Low Resource Hardware,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Efficient V oice Trigger Detection for Low Resource Hardware,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.506092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ca2235bb-1f43-4566-8e74-a9a38429c89d · outbound

This paper cites Multichannel Voice Trigger Detection Based on Transform-average-concatenate.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Multichannel Voice Trigger Detection Based on Transform-average-concatenate

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-09T20:20:59.263101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aae3cc85-6e7f-4d00-b069-e2762db084c1 · outbound

This paper cites Accurate Detection of Wake Word Start and End Using a CNN,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Accurate Detection of Wake Word Start and End Using a CNN,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.497178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b76181ae-2991-4843-afaf-29c6e9742f5a · outbound

This paper cites Low-resource Low-footprint Wake-word Detec- tion using Knowledge Distillation,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Low-resource Low-footprint Wake-word Detec- tion using Knowledge Distillation,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.488115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 46e1db43-40d3-4262-937b-951bbd0cc1b3 · outbound

This paper cites Convolutional neural networks for small-footprint keyword spotting,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Convolutional neural networks for small-footprint keyword spotting,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.478648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5210ff4e-e116-4ab1-a79d-888765c123ab · outbound

This paper cites Keyword spotting for google assistant using contextual speech recognition,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Keyword spotting for google assistant using contextual speech recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.470328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d15b3df-0e73-4450-84e8-9fcc72243bcc · outbound

This paper cites Contrastive speech mixup for low-resource keyword spotting,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Contrastive speech mixup for low-resource keyword spotting,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.461170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8412ed77-3cd1-4a24-94f0-51a438590792 · outbound

This paper cites A multimodal approach to device-directed speech detection with large language models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions A multimodal approach to device-directed speech detection with large language models,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.452594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 860f977e-0f5b-4ed3-a46e-e0a184380191 · outbound

This paper cites Learning when to listen: detecting system-addressed speech in human-human-computer dialog,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Learning when to listen: detecting system-addressed speech in human-human-computer dialog,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.443887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 509ad48b-53c4-46e5-97c3-60c9318c08a4 · outbound

This paper cites Device-directed utterance detection,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Device-directed utterance detection,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.434812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa08ea72-9b41-40a6-bda7-f5a36a376d30 · outbound

This paper cites Device-directed speech detection: Regularization via distillation for weakly-supervised models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Device-directed speech detection: Regularization via distillation for weakly-supervised models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.425821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19a59fd6-e635-459c-8792-542c59c93044 · outbound

This paper cites Streaming Transformer for Hardware Efficient V oice Trigger Detection and False Trigger Mitigation,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Streaming Transformer for Hardware Efficient V oice Trigger Detection and False Trigger Mitigation,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.416237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d728883-85f0-43d0-b05a-2e821a15e0d8 · outbound

This paper cites Lattice-based improvements for voice triggering using graph neural networks,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Lattice-based improvements for voice triggering using graph neural networks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.406804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 89376b3a-efdf-4f42-9612-cb340d402641 · outbound

This paper cites V oice trigger detection from lvcsr hypothesis lattices using bidirectional lattice recurrent neural networks,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions V oice trigger detection from lvcsr hypothesis lattices using bidirectional lattice recurrent neural networks,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.398050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9d97c1f0-5f5f-4d00-8d3f-7ea29f74a97a · outbound

This paper cites Exploring attention mechanism for acoustic-based classification of speech utterances into system-directed and non-system-directed,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Exploring attention mechanism for acoustic-based classification of speech utterances into system-directed and non-system-directed,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.388777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cc11b4e8-a369-4360-9c4d-24c615e8657c · outbound

This paper cites Less is more: A unified architecture for device- directed speech detection with multiple invocation types,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Less is more: A unified architecture for device- directed speech detection with multiple invocation types,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.379798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2783894e-3a8e-4962-9a17-db55186ed5cf · outbound

This paper cites A Study for Improving Device-Directed Speech De- tection Toward Frictionless Human-Machine Interaction,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions A Study for Improving Device-Directed Speech De- tection Toward Frictionless Human-Machine Interaction,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.370313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 833d2349-e460-49be-a96e-5d6cfa999c25 · outbound

This paper cites Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.891002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 909051c9-eb4e-4683-b661-381f2ed5dbd1 · outbound

This paper cites Multimodal large language models with fusion low rank adaptation for device directed speech detection,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Multimodal large language models with fusion low rank adaptation for device directed speech detection,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.361278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aea614d5-84f7-41de-9d86-e9eede63427c · outbound

This paper cites Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-09T20:20:59.240915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7bcb1b3f-f61f-446b-becd-a5ecf9799726 · outbound

This paper cites Apple intelligence foundation language models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Apple intelligence foundation language models,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.901528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b93b0366-5968-410f-8bf8-0d92bf27c0ad · outbound

This paper cites Large language models are zero-shot reasoners,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Large language models are zero-shot reasoners,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.352137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6200b4eb-10aa-4022-8fbd-fd871087f912 · outbound

This paper cites Language Models are Few-Shot Learners.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Language Models are Few-Shot Learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.912349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0791a6b4-b47a-4795-a295-f704924594c8 · outbound

This paper cites Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.916296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee24ee33-d0ea-43ee-a8cd-093623714cdf · outbound

This paper cites SALMONN: Towards generic hearing abilities for large language models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions SALMONN: Towards generic hearing abilities for large language models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.343108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4a5677dc-a289-47f0-8369-c96da10ea8fe · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.924487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cdb25bb-6333-4523-afd6-851f14efbbbe · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.928239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd45b56f-1a13-4d18-8351-cc832aae6ad6 · outbound

This paper cites Pengi: An audio language model for audio tasks,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Pengi: An audio language model for audio tasks,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.333627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f6ea27e2-f63a-4fc7-9ea2-9fd4d2f5a677 · outbound

This paper cites Coding dialogs with the damsl annota- tion scheme,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Coding dialogs with the damsl annota- tion scheme,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.324148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ac7f3887-7acb-4211-8c45-d9df3b98897e · outbound

This paper cites Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.313695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9ed93ffe-b75a-455c-8f61-6beafef2717c · outbound

This paper cites Attention is all you need,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Attention is all you need,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.303711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0b56fcd9-dbb9-434f-9f7b-2f1ec0e7c116 · outbound

This paper cites Robust Speech Recognition via Large-Scale Weak Supervision.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Robust Speech Recognition via Large-Scale Weak Supervision

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.946422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daab60d2-a255-466d-9ce8-6c52c3b5474b · outbound

This paper cites Qwen Technical Report.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Qwen Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.950073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1673c25c-5f5e-45fe-961c-4143fef101a9 · outbound

This paper cites Quan- tizable transformers: Removing outliers by helping attention heads do nothing,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Quan- tizable transformers: Removing outliers by helping attention heads do nothing,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.293801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1feded89-0bfd-4f35-9626-dd35b84f5e8a · outbound

This paper cites LoRA: Low-rank adaptation of large language models,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions LoRA: Low-rank adaptation of large language models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.284045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59208eb0-7fda-4c43-9c7f-51dde672b5e8 · outbound

This paper cites Decoupled weight decay regu- larization,.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Decoupled weight decay regu- larization,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:20:59.273882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d51af6b7-8950-4124-939d-b0fe2db28e8e · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T20:20:58.963820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.