Locality enhanced dynamic biasing and sampling strategies for contextual ASR

Md Asif Jalal, Pablo Peso Parada, George Pavlidis, Vasileios Moschopoulos, Karthikeyan Saravanan +6 more
1/23/2024
eess.AScs.CLcs.SD

No confident code implementation found for this paper.

Abstract

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are selected from a large pool of phrases following a sampling strategy. In this work we firstly analyse different sampling strategies to provide insights into the training of CB for ASR with correlation plots between the bias embeddings among various training stages. Secondly, we introduce a neighbourhood attention (NA) that localizes self attention (SA) to the nearest neighbouring frames to further refine the CB output. The results show that this proposed approach provides on average a 25.84% relative WER improvement on LibriSpeech sets and rare-word evaluation compared to the baseline.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search

87% match2024

Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation

87% match2024

Contextualized Automatic Speech Recognition with Dynamic Vocabulary

87% match2024

Improving ASR Contextual Biasing with Guided Attention

87% match2024

Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling

86% match2025

Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition

85% match2023

Cite this paper

@article{jalal2024locality,
  title  = {Locality enhanced dynamic biasing and sampling strategies for contextual ASR},
  author = {Md Asif Jalal and Pablo Peso Parada and George Pavlidis and Vasileios Moschopoulos and Karthikeyan Saravanan and Chrysovalantis-Giorgos Kontoulis and Jisi Zhang and Anastasios Drosou and Gil Ho Lee and Jungin Lee and Seokyeong Jung},
  year   = {2024},
  eprint = {2401.13146},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.13146v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.13146.svg)](https://codeofpaper.com/paper/2401.13146)

Discussion