Related papers: ParaTTS: Learning Linguistic and Prosodic Cross-se…

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

Modern neural TTS systems are capable of generating natural and expressive speech when provided with sufficient amounts of training data. Such systems can be equipped with prosody-control functionality, allowing for more direct shaping of…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods…

Neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the synthetic speech often represents the average prosodic style of the database instead of having more versatile prosodic…

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…

Generating a long, coherent text such as a paragraph requires a high-level control of different levels of relations between sentences (e.g., tense, coreference). We call such a logical connection between sentences as a (paragraph) flow. In…

Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language…

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration)…

To simplify the generation process, several text-to-speech (TTS) systems implicitly learn intermediate latent representations instead of relying on predefined features (e.g., mel-spectrogram). However, their generation quality is…

Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and…

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…

Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis. As a result, a single neural network replaced laborious feature engineering with…

End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…

We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work…

This chapter presents a novel approach to brain-to-speech (BTS) synthesis from intracranial electroencephalography (iEEG) data, emphasizing prosody-aware feature engineering and advanced transformer-based models for high-fidelity speech…

Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference.…

Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…

Recent TTS systems are able to generate prosodically varied and realistic speech. However, it is unclear how this prosodic variation contributes to the perception of speakers' emotional states. Here we use the recent psychological paradigm…