41 datasets found

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...

The dataset used for this study was collected for a mental health assessment project conducted at the University of Maryland School of Medicine in collaboration with the...

The CHiME-4 dataset is a large-scale speech recognition dataset, containing over 2 hours of speech from 6 channels.

The dataset used for the task of mispronunciation detection for second language learners.

The GTZAN dataset is a comprehensive collection of 1000 audio tracks, each 30 seconds long, representing ten diverse music genres.

The LJSpeech-1.1 dataset is a large-scale speech dataset containing approximately 24 hours of single-speaker speech recorded at 22 050 Hz.

The dataset used in this paper is a speech dataset, which is used for training and testing the proposed LaDiffCodec model.

The dataset used in this paper is a speech dataset, which is used for training and testing the proposed LaDiffCodec model.

The VCTK corpus is an English multi-speaker dataset, with 44 hours of audio spoken by 109 native English speakers.

The CSTR VCTK Corpus is a dataset of speech recordings of 109 speakers, each with 20 utterances.

The ASVspoof 2021 LA dataset is used for testing the generalization capabilities of our model.

The ASVspoof 2019 LA dataset encompasses three types of speaker representation: d-vector, one-hot embedding, and VAE.

The LJ speech dataset is a dataset of speech samples recorded from a single speaker reading passages from 7 non-fiction books.

The Maestro dataset contains MIDI and audio files of recorded performances from piano performance competitions.

Generating coherent and natural movement is the key challenge in video generation. This research proposes to condense video generation into a problem of motion generation, to...

The Librispeech dataset is a large-scale speaker-dependent speech corpus containing 1080 hours of speech, 5600 utterances, and 1000 speakers.

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature...

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...

The CASIA dataset contains palmprint images from over 100 individuals, captured under various lighting conditions.