REVIEW 4 cited by
MaLa-ASR: Multimedia-Assisted LLM-Based ASR
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
As more and more information-rich data like video become available, utilizing multi-modal auxiliary information to enhance audio tasks has sparked widespread research interest. The recent surge in research on LLM-based audio models provides fresh perspectives for tackling audio tasks. Given that LLM can flexibly ingest multiple inputs, we propose MaLa-ASR, an LLM-based ASR model that can integrate textual keywords extracted from presentation slides to improve recognition of conference content. MaLa-ASR yields average WERs of 9.4% and 11.7% on the L95 and S95 subsets of the SlideSpeech corpus, representing a significant relative WER drop of 27.9% and 44.7% over the baseline model reported in SlideSpeech. MaLa-ASR underscores LLM's strong performance in speech tasks and the capability to integrate auxiliary information conveniently. By adding keywords to the input prompt, the biased word error rate (B-WER) reduces relatively by 46.0% and 44.2%, establishing a new SOTA on this dataset.
Forward citations
Cited by 4 Pith papers
-
Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling
A contextual speech recognition method that combines list-, phrase-, and token-level relevance scores and then filters the personal word list improves F1 on varying-length biasing lists relative to three baselines.
-
Improving Contextual ASR via Multi-grained Fusion with Large Language Models
A multi-grained fusion method that jointly uses token-level and phrase-level scores from ASR and LLM improves keyword recognition in contextual ASR.
-
Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems
Adding cross-utterance audio context to Conformer-Transducer ASR reduces WER/CER by 0.5 to 1.1 absolute points on four benchmarks, and a splicing-based batch scheme cuts training time by up to about 19%.
-
Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
Tiny-Align aligns ASR audio features with an LLM's text-embedding space via a trained projector, claiming 50x faster convergence and improved ROUGE scores for edge ASR-LLM personalization.
Discussion (0). Continue with ORCID to comment.