61 datasets found

The ICSI Meeting Corpus

The BVCC dataset is a newly collected MOS dataset that contains 7106 English samples from previous Bliz-zard Challenge for TTS and Voice Conversion Challenge.

Proprietary dataset consisting of 57 hours of Korean speech recorded by 38 professional voice actors.

The LibriTTS-R dataset, used as a reference speech dataset for the proposed TTSDS benchmark.

The dataset used for the proposed TTSDS benchmark, which includes 35 TTS systems developed between 2008 and 2024.

MIX dataset

Unified codec language models for speech recognition, synthesis, and translation.

Neural codec language models are zero-shot text to speech synthesizers.

A large language model that can speak and listen.

A comprehensive collection of contemporary codec models, resulting in the creation of the CodecFake dataset.

The dataset used in the paper for automatic prosody prediction for Chinese speech synthesis using BLSTM-RNN and embedding features.

Aozorabunko dataset used for pre-training of PnG BERT model.

Wikipedia2 and Aozorabunko datasets used for pre-training of PnG BERT model.

Minimally-supervised speech synthesis method based on diffusion models with minimal supervision. Introduces the CTAP method as an intermediate semantic representation and uses...

A speech corpus of size 7,000 used for training and validation of the FCI module.

Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot TTS....

Development of HMM-based Indonesian speech synthesis.

A small-footprint, fast, stable network for on-device text-to-speech synthesis

The TIMIT corpus is a large database of speech recordings used for speaker recognition and speech synthesis tasks.

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...