Domain-aware Neural Language Models for Speech Recognition

Liu, Linda; Gu, Yile; Gourav, Aditya; Gandhe, Ankur; Kalmane, Shashank; Filimonov, Denis; Rastrow, Ariya; Bulyko, Ivan

doi:10.48550/arxiv.2101.03229

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• SlotWER is computed alongside the WER for the evaluation of SLU systems [19]. However, we need a unified evaluation framework that is direct and objective and can be used for accessing the quality of the ASR transcript for end usability.…”

Section: Introductionmentioning

confidence: 99%

Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability

Roy

2021

Preprint

View full text Add to dashboard Cite

Recent advances in supervised, semi-supervised and selfsupervised deep learning algorithms have shown significant improvement in the performance of automatic speech recognition (ASR) systems. The state-of-the-art systems have achieved a word error rate (WER) less than 5%. However, in the past, researchers have argued the non-suitability of the WER metric for the evaluation of ASR systems for downstream tasks such as spoken language understanding (SLU) and information retrieval. The reason is that the WER works at the surface level and does not include any syntactic and semantic knowledge. The current work proposes Semantic-WER (SWER), a metric to evaluate the ASR transcripts for downstream applications in general. The SWER can be easily customized for any downstream task.

show abstract

Section: Introductionmentioning

confidence: 99%

Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability

Roy

2021

Preprint

View full text Add to dashboard Cite

show abstract

Domain-aware Neural Language Models for Speech Recognition

Cited by 1 publication

References 18 publications

Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability

Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability

Contact Info

Product

Resources

About