Articles tagged with #benchmarks




Dear Diarization: Using MFA 2.1 to assign speaker labels to utterances

Evaluating speaker diarization in MFA for English and Korean



Playing around with PolyglotDB

Following some updates to PolyglotDB, let’s play around with some recordings and extract some acoustic measures



How much data do you need for a good MFA alignment?

Forced alignment is sometimes more art than science, but let’s try to establish some rules of thumb for how much data you might need when aligning a corpus



Update on Montreal Forced Aligner performance

Take a look at how MFA 2.0 stacks up against the first version and a couple of other aligners in English