Combining Hybrid and End-to-End Approaches for the OpenASR20 Challenge

Alumäe, Tanel; Kong, Jiaming

doi:10.21437/interspeech.2021-1086

Search citation statements

Order By: Relevance

Paper Sections

Select...

Dnn-based Approach To Build Acoustic Model1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2024

Publication Types

Select...

Book3

Article1

Other1

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 5 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For most languages, the trends are similar for the two languages: although the absolute WERs across languages are very different, first-pass decoding with either of the two acoustic models yields similar WERs. In terms of first pass results, lattice re-scoring and combining lead to 5-10% relative improvement [79].…”

Section: Dnn-based Approach To Build Acoustic Modelmentioning

confidence: 99%

Frontier Research on Low-Resource Speech Recognition Technology

Slam,

Li,

Urouvas

2023

Sensors

View full text Add to dashboard Cite

With the development of continuous speech recognition technology, users have put forward higher requirements in terms of speech recognition accuracy. Low-resource speech recognition, as a typical speech recognition technology under restricted conditions, has become a research hotspot nowadays because of its low recognition rate and great application value. Under the premise of low-resource speech recognition technology, this paper reviews the research status of feature extraction and acoustic models, and conducts research on resource expansion. Especially in terms of the technical challenges faced by this technology, solutions are proposed, and future research directions are prospected.

show abstract

Section: Dnn-based Approach To Build Acoustic Modelmentioning

confidence: 99%