Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs | Paper Citation Record

Observation d966a59c-cd8c-476f-a0b9-3b35211818d5 · outbound

This paper cites The application of hidden Markov models in speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs The application of hidden Markov models in speech recognition,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.749417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d45345d8-d7fe-4b76-9a97-2b18a0f7cf52 · outbound

This paper cites A tutorial on hidden Markov models and selected applications in speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs A tutorial on hidden Markov models and selected applications in speech recognition,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.732459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aeb462a3-2d33-4f03-b2df-157037d21e14 · outbound

This paper cites Montreal Forced Aligner: Trainable text-speech alignment using Kaldi,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Montreal Forced Aligner: Trainable text-speech alignment using Kaldi,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.745973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6f3e1311-fec4-47c0-93b7-664107fb0ff3 · outbound

This paper cites Less peaky and more accurate CTC forced alignment by label priors,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Less peaky and more accurate CTC forced alignment by label priors,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.747709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 50d9969e-337f-4be5-8045-927e882fac6d · outbound

This paper cites Tradition or inno- vation: A comparison of modern asr methods for forced alignment,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Tradition or inno- vation: A comparison of modern asr methods for forced alignment,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.726454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 810712ad-b30a-4540-a290-e964861f9a83 · outbound

This paper cites End-to-end speech recognition: A survey,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs End-to-end speech recognition: A survey,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.742389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 857bdb36-5b2c-4174-a6c7-da2b75041ccf · outbound

This paper cites Connection- ist temporal classification: labelling unsegmented sequence data with recurrent neural networks,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Connection- ist temporal classification: labelling unsegmented sequence data with recurrent neural networks,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.734322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c54e7385-2112-4562-ae87-af83100b8fae · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Sequence Transduction with Recurrent Neural Networks

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.593477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f47e5bcf-50fd-4cae-9ac1-d048fd931d7a · outbound

This paper cites Attention-based models for speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Attention-based models for speech recognition,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.760103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3a4df90a-b69d-4449-939a-776b5f7ec512 · outbound

This paper cites Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.758483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 68e4eecd-db03-4145-b76c-bb713c403e0d · outbound

This paper cites Improved training of end-to- end attention models for speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Improved training of end-to- end attention models for speech recognition,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.736486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9c46d745-96f8-469c-91f5-b5f7f68023dc · outbound

This paper cites SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.728620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7ce561c0-0674-4ab2-b590-4b95fa456615 · outbound

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

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.581542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 399b1390-7481-4696-a009-023215cc1122 · outbound

This paper cites LLMs and Speech: Integration vs. Combination.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs LLMs and Speech: Integration vs. Combination

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.588062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ae15985d-1df6-4eb3-bf05-092468164318 · outbound

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

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Robust speech recognition via large-scale weak supervision,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.781600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60c69c61-7a2a-4850-a787-41f8ad045c9d · outbound

This paper cites WhisperX: Time-accurate speech transcription of long-form audio,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs WhisperX: Time-accurate speech transcription of long-form audio,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.754796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b199a002-115e-49f6-bdbb-7ae779d26b93 · outbound

This paper cites CrisperWhisper: Accurate timestamps on verbatim speech transcriptions,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs CrisperWhisper: Accurate timestamps on verbatim speech transcriptions,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.792339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f96fb2a6-db40-4145-a810-8a5fed11c603 · outbound

This paper cites Whisper has an internal word aligner,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Whisper has an internal word aligner,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.788911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fb35d85a-b9c4-4f0e-98b6-f83dc377ac08 · outbound

This paper cites Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.605092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation db745102-9d9f-4963-8f66-cf92f78b966d · outbound

This paper cites DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.584712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8fa22560-df82-4b40-b451-dfd3f57a013f · outbound

This paper cites Available: https://arxiv.org/abs/2601.18220.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Available: https://arxiv.org/abs/2601.18220

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-10T20:27:36.599158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 46faea88-3537-461b-89de-0bdc9534c20e · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.610300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b5413ae3-61ac-42fb-8423-5534e301fb5b · outbound

This paper cites Right Label Context in End-to-End Training of Time-Synchronous ASR Models.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Right Label Context in End-to-End Training of Time-Synchronous ASR Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.590845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14c126d0-ee23-44f9-996c-8862d3fdc5e3 · outbound

This paper cites Saliency-driven word alignment interpretation for neural machine translation,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Saliency-driven word alignment interpretation for neural machine translation,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.756579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 80b417cf-69a4-4c7a-8385-efd91f5a14d2 · outbound

This paper cites Joint CTC/attention decoding for end-to-end speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Joint CTC/attention decoding for end-to-end speech recognition,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.786985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b14ce76-a4ce-442e-a644-f717c54a511d · outbound

This paper cites Scaling speech tech- nology to 1,000+ languages,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Scaling speech tech- nology to 1,000+ languages,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.785158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 141c56c5-d111-482b-ad7d-12872cc90159 · outbound

This paper cites TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.724159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7e474b36-d535-4835-af3f-56cce3229774 · outbound

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

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.765630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 909c4e4a-76a3-4b23-afcd-9256897df7fd · outbound

This paper cites Automatic phoneme recognition on TIMIT dataset with Wav2Vec 2.0,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Automatic phoneme recognition on TIMIT dataset with Wav2Vec 2.0,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.769218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation faa55225-00b2-46c4-bc19-88ece0e60d4c · outbound

This paper cites XLS-R: Self-supervised cross-lingual speech representation learning at scale,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs XLS-R: Self-supervised cross-lingual speech representation learning at scale,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.776543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f8a77ee5-878e-41e4-9de1-0f4b186747bb · outbound

This paper cites Fast conformer with linearly scalable attention for efficient speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Fast conformer with linearly scalable attention for efficient speech recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.783272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e61fd5aa-ba69-4030-87ff-2ca320b7a803 · outbound

This paper cites OWSM v4: Improving open whisper-style speech models via data scaling and cleaning,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs OWSM v4: Improving open whisper-style speech models via data scaling and cleaning,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.790646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 192f1e8d-8680-45ed-9418-f3228e4196ea · outbound

This paper cites OWSM-CTC: An open encoder-only speech foundation model for speech recognition, translation, and language identification,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs OWSM-CTC: An open encoder-only speech foundation model for speech recognition, translation, and language identification,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.767507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9eaa9a3-1064-4281-b3d4-2894d73a38a3 · outbound

This paper cites Stateful conformer with cache-based inference for streaming automatic speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Stateful conformer with cache-based inference for streaming automatic speech recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.770999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6c777291-1348-41e2-85d0-09d8e82d52cf · outbound

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

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Efficient sequence transduction by jointly predicting tokens and durations,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.763726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b966bde-edd6-4365-83b5-d13f50453e29 · outbound

This paper cites Emformer: Efficient memory transformer based acoustic model for low latency streaming speech recognition,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Emformer: Efficient memory transformer based acoustic model for low latency streaming speech recognition,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.753093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bfa1780e-6102-4e67-b507-77b61a9746c3 · outbound

This paper cites TorchAudio: Building blocks for audio and speech processing,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs TorchAudio: Building blocks for audio and speech processing,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.778265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8d6223ec-4015-456d-ad38-511db9c02f77 · outbound

This paper cites OWLS: Scaling laws for multilingual speech recognition and translation models,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs OWLS: Scaling laws for multilingual speech recognition and translation models,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.762010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3db9f10c-f72e-4a63-802f-e476e6864eec · outbound

This paper cites Voxtral.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Voxtral

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.607654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0f200d49-b50b-44bd-b3c5-d4edadfefd4d · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.602301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2d604f11-08f7-4c62-86ce-c490b9e6441f · outbound

This paper cites Less is more: Accurate speech recognition & translation without web-scale data,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Less is more: Accurate speech recognition & translation without web-scale data,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.740428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5f231df0-a75d-4f6e-885a-dee428eb86c7 · outbound

This paper cites TIMIT acoustic-phonetic continuous speech corpus,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs TIMIT acoustic-phonetic continuous speech corpus,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.779980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84564faf-fd3a-448e-abb3-4dfb050d909e · outbound

This paper cites The Buckeye corpus of conversational speech: Labeling conventions and a test of transcriber reliability,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs The Buckeye corpus of conversational speech: Labeling conventions and a test of transcriber reliability,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.744190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cc9ab90d-6d58-4ff2-8ea6-9c477c6d02dd · outbound

This paper cites Learning important features through propagating activation differences,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Learning important features through propagating activation differences,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.738421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d7e1feb3-8b81-4716-a2eb-1b8bbd2bf388 · outbound

This paper cites Towards better understanding of gradient-based attribution methods for deep neural networks,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Towards better understanding of gradient-based attribution methods for deep neural networks,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.751310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2290b8b4-2ec2-4619-9cca-56ae8b26d3dc · outbound

This paper cites SmoothGrad: removing noise by adding noise.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs SmoothGrad: removing noise by adding noise

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-10T20:27:36.596077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ba70317-85aa-43c0-a86f-3db544ec09e8 · outbound

This paper cites Sanity checks for saliency maps,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Sanity checks for saliency maps,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.772994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 41457776-1484-4b60-adca-67d6ee3eee18 · outbound

This paper cites Available: https://proceedings.neurips.cc/paper files/ paper/2018/file/294a8ed24b1ad22ec2e7efea049b8737-Paper.pdf.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Available: https://proceedings.neurips.cc/paper files/ paper/2018/file/294a8ed24b1ad22ec2e7efea049b8737-Paper.pdf

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.794010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c0fb4029-8cc0-4385-9891-18f15ccd52b5 · outbound

This paper cites Axiomatic attribution for deep networks,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Axiomatic attribution for deep networks,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.730491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bb1834f8-f027-4183-b870-7fb7c94926f4 · outbound

This paper cites Improving performance of deep learning models with axiomatic attribution priors and expected gradients,.

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs Improving performance of deep learning models with axiomatic attribution priors and expected gradients,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T20:27:36.774812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers