Related papers: Improve Bilingual TTS Using Dynamic Language and P…
Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…
Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…
In recent years, emotional Text-to-Speech (TTS) synthesis and emphasis-controllable speech synthesis have advanced significantly. However, their interaction remains underexplored. We propose Emphasis Meets Emotion TTS (EME-TTS), a novel…
While generative text-to-speech (TTS) models approach human-level quality, monolithic metrics fail to diagnose fine-grained acoustic artifacts or explain perceptual collapse. To address this, we propose TTS-PRISM, a multi-dimensional…
Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate…
Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality…
This paper presents a novel design of attention model for text-independent speaker verification. The model takes a pair of input utterances and generates an utterance-level embedding to represent speaker-specific characteristics in each…
Tibetan text-to-speech (TTS) has long been challenged by scarce speech resources, significant dialectal variation, and the complex mapping between written text and spoken pronunciation. To address these issues, this work presents, to the…
Video dubbing aims to generate high-fidelity speech that is precisely temporally aligned with the visual content. Existing methods still suffer from limitations in speech naturalness and audio-visual synchronization, and are limited to…
By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is…
People may be puzzled by the fact that voice over recordings data sets exist in addition to Text-to-Speech (TTS), Synthesis system advancements, albeit this is not the case. The goal of this study is to explain the relevance of TTS as well…
Great progress has been made in unsupervised bilingual lexicon induction (UBLI) by aligning the source and target word embeddings independently trained on monolingual corpora. The common assumption of most UBLI models is that the embedding…
End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the…
We study the problem of multilingual masked language modeling, i.e. the training of a single model on concatenated text from multiple languages, and present a detailed study of several factors that influence why these models are so…
The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…
Producing synthetic voice, similar to human-like sound, is an emerging novelty of modern interactive media systems. Text-To-Speech (TTS) systems try to generate synthetic and authentic voices via text input. Besides, well known and familiar…
The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models show state-of-the-art performance on a wide range of tasks including reading comprehension,…
Multilingual sentence encoders (MSEs) are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality, a loss of…
Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training…
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…