Researchers share framework for more accurate speech recognition

Episode 213 September 12, 2022 00:03:54
Researchers share framework for more accurate speech recognition
Localization Today
Researchers share framework for more accurate speech recognition

Sep 12 2022 | 00:03:54

/

Hosted By

Eddie Arrieta

Show Notes

Despite the prevalence of automatic speech recognition software, it’s obvious that these tools could use some improvement, especially when speaking with a non-standard accent or in a slightly noisy environment. According to the team of researchers behind the paper, this can be particularly difficult to get right in Mandarin Chinese.

Other Episodes

Episode 271

November 18, 2022 00:03:21
Episode Cover

Zoom adds sign language interpretation feature

Zoom announced earlier this month that it’s added a new feature to make its video communication platform more accessible to deaf and hard-of-hearing users:...

Listen

Episode 59

April 02, 2022 00:08:43
Episode Cover

Differences between US and UK English that language professionals should know

The different dialects of English present an interesting challenge for professionals working in language services.

Listen

Episode 117

May 12, 2022 00:03:11
Episode Cover

Meta gives researchers full access to its large language model, OPT-175B

Earlier this month, Meta announced the development of its large language model Open Pretrained Transformer (OPT-175B), which has been trained on 175 billion parameters...

Listen