Retrieval Augmented Correction of Named Entity Speech Recognition Errors

no code implementations • 9 Sep 2024 • Ernest Pusateri, Anmol Walia, Anirudh Kashi, Bortik Bandyopadhyay, Nadia Hyder, Sayantan Mahinder, Raviteja Anantha, Daben Liu, Sashank Gondala

In recent years, end-to-end automatic speech recognition (ASR) systems have proven themselves remarkably accurate and performant, but these systems still have a significant error rate for entity names which appear infrequently in their training data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants

no code implementations • 2 Nov 2023 • Youyuan Zhang, Sashank Gondala, Thiago Fraga-Silva, Christophe Van Gysel

On-device Virtual Assistants (VAs) powered by Automatic Speech Recognition (ASR) require effective knowledge integration for the challenging entity-rich query recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Error-driven Pruning of Language Models for Virtual Assistants

no code implementations • 14 Feb 2021 • Sashank Gondala, Lyan Verwimp, Ernest Pusateri, Manos Tsagkias, Christophe Van Gysel

We customize entropy pruning by allowing for a keep list of infrequent n-grams that require a more relaxed pruning threshold, and propose three methods to construct the keep list.