The AISHELL-1 dataset is a Mandarin speech corpus, consisting of 178 hours of speech, with 11 domains and 400 speakers from different accent areas in China.
The TIMIT corpus is a widely used benchmark for speech recognition tasks. It contains 3,696 training utterances from 462 speakers, excluding the SA sentences. The core test set...
Voice conversion (VC) is a technique that alters the voice of a source speaker to a target style, such as speaker identity, prosody, and emotion, while keeping the linguistic...
Speaker recognition aims to identify speaker information from input speech. A type of speaker recognition is speaker verification (SV). It determines whether the test speaker's...
A popular text-based VC approach is to use an automatic speech recognition (ASR) model to extract phonetic posteriorgram (PPG) as content representation.
