Related papers: CosyAccent: Duration-Controllable Accent Normaliza…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

In our prior works, we introduced a scalable streaming speech synthesis model, CosyVoice 2, which integrates a large language model (LLM) and a chunk-aware flow matching (FM) model, and achieves low-latency bi-streaming speech synthesis and…

Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…

Neural text-to-speech (TTS) approaches generally require a huge number of high quality speech data, which makes it difficult to obtain such a dataset with extra emotion labels. In this paper, we propose a novel approach for emotional TTS…

The availability of data in expressive styles across languages is limited, and recording sessions are costly and time consuming. To overcome these issues, we demonstrate how to build low-resource, neural text-to-speech (TTS) voices with…

Training a high performance end-to-end speech (E2E) processing model requires an enormous amount of labeled speech data, especially in the era of data-centric artificial intelligence. However, labeled speech data are usually scarcer and…

The development of high-performance, on-device keyword spotting (KWS) systems for ultra-low-power hardware is critically constrained by the scarcity of specialized, multi-command training datasets. Traditional data collection through human…

Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they must be recorded in a studio. This requirement currently…

Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS. However, the presence of reduced articulation, fillers, repetitions, and other disfluencies in spontaneous speech make the…

Dysarthric speech exhibits high variability and limited labeled data, posing major challenges for both automatic speech recognition (ASR) and assistive speech technologies. Existing approaches rely on synthetic data augmentation or speech…

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

This paper proposes a method for selecting training data for text-to-speech (TTS) synthesis from dark data. TTS models are typically trained on high-quality speech corpora that cost much time and money for data collection, which makes it…

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…

This paper proposes a new approach to duration modelling for statistical parametric speech synthesis in which a recurrent statistical model is trained to output a phone transition probability at each timestep (acoustic frame). Unlike…

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tracing models using…

Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from…

We present an end-to-end text-to-speech (TTS) synthesis system that generates audio and synchronized tongue motion directly from text. This is achieved by adapting a 3D model of the tongue surface to an articulatory dataset and training a…

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

Humans often speak in a continuous manner which leads to coherent and consistent prosody properties across neighboring utterances. However, most state-of-the-art speech synthesis systems only consider the information within each sentence…