Related papers: Training Universal Vocoders with Feature Smoothing…
A text-to-speech (TTS) model trained to reconstruct speech given text tends towards predictions that are close to the average characteristics of a dataset, failing to model the variations that make human speech sound natural. This problem…
Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often undermined by evolving…
In this paper, we present a vocoder-free framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients. Unlike conventional two-stage…
This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…
Text-to-Speech (TTS) systems in Lombard speaking style can improve the overall intelligibility of speech, useful for hearing loss and noisy conditions. However, training those models requires a large amount of data and the Lombard effect is…
Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…
Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or…
This paper explores the potential universality of neural vocoders. We train a WaveRNN-based vocoder on 74 speakers coming from 17 languages. This vocoder is shown to be capable of generating speech of consistently good quality (98% relative…
Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language…
Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of…
Neural text-to-speech (TTS) can provide quality close to natural speech if an adequate amount of high-quality speech material is available for training. However, acquiring speech data for TTS training is costly and time-consuming,…
Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology…
Neural-based text-to-speech (TTS) systems achieve very high-fidelity speech generation because of the rapid neural network developments. However, the huge labeled corpus and high computation cost requirements limit the possibility of…
Text-to-speech (TTS) and text-to-music (TTM) models face significant limitations in instruction-based control. TTS systems usually depend on reference audio for timbre, offer only limited text-level attribute control, and rarely support…
Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient…
Automatic transcription of monophonic/polyphonic music is a challenging task due to the lack of availability of large amounts of transcribed data. In this paper, we propose a data augmentation method that converts natural speech to singing…
Many speech synthesis datasets, especially those derived from audiobooks, naturally comprise sequences of utterances. Nevertheless, such data are commonly treated as individual, unordered utterances both when training a model and at…
Custom voice is to construct a personal speech synthesis system by adapting the source speech synthesis model to the target model through the target few recordings. The solution to constructing a custom voice is to combine an adaptive…
For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality.…