Jun 24, 2020 · We introduce the problem of adapting a black-box, cloud-based ASR system to speech from a target accent.

We introduce the problem of adapting a black-box, cloud-based. ASR system to speech from a target accent. While leading online ASR services obtain ...

This work proposes a novel coupling of an open-source accent-tuned local model with the black-box service where the output from the service guides ...

We introduce the problem of adapting a black-box, cloud-based ASR system to speech from a target accent. While leading online ASR services obtain impressive ...

Adaptation of a black-box ASR system is of great interest but there are few prior works. [10] builds a local accent-tuned ASR model and uses the output from ...

Jun 24, 2020 · We introduce the problem of adapting a black-box, cloud-based. ASR system to speech from a target accent. While leading.

Kartik Khandelwal, Preethi Jyothi, Abhijeet Awasthi, Sunita Sarawagi: Black-box Adaptation of ASR for Accented Speech. CoRR abs/2006.13519 (2020).

Therefore, this method is applicable to adapting a black-box, cloud-based speech-to-text system. ... Sarawagi, “Black- box adaptation of ASR for accented speech,” ...

This work proposes a novel accent adaptation approach for end-to-end ASR systems using cross-attention with a trainable set of codebooks that capture ...

The baseline ASR is trained on speech data pooled from all five accents. The ... polyphone decision tree adaptation for accented speech recognition. In ...