Related papers: Enhancing TTS Stability in Hebrew using Discrete S…

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and conditioning the training process on the speaker's identity or…

Recent large language models (LLMs) have made great progress in the field of text-to-speech (TTS), but they still face major challenges in synthesizing fine-grained emotional speech in an interpretable manner. Traditional methods rely on…

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). How to control the intensity of accent in the process of TTS is a very interesting research direction, and has…

Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.…

This paper introduces a novel approach to Dialogue State Tracking (DST) that leverages Large Language Models (LLMs) to generate natural language descriptions of dialogue states, moving beyond traditional slot-value representations.…

Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speech alignment and…

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…

Voice communication in bandwidth-constrained environments--maritime, satellite, and tactical networks--remains prohibitively expensive. Traditional codecs struggle below 1 kbps, while existing semantic approaches (STT-TTS) sacrifice prosody…

Personalizing a speech synthesis system is a highly desired application, where the system can generate speech with the user's voice with rare enrolled recordings. There are two main approaches to build such a system in recent works: speaker…

The recent text-to-speech (TTS) has achieved quality comparable to that of humans; however, its application in spoken dialogue has not been widely studied. This study aims to realize a TTS that closely resembles human dialogue. First, we…

Disentanglement of a speaker's timbre and style is very important for style transfer in multi-speaker multi-style text-to-speech (TTS) scenarios. With the disentanglement of timbres and styles, TTS systems could synthesize expressive speech…

To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are…

In most cases, bilingual TTS needs to handle three types of input scripts: first language only, second language only, and second language embedded in the first language. In the latter two situations, the pronunciation and intonation of the…

Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges,…

While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail…

Text-to-speech (TTS) systems offer the opportunity to compensate for a hearing loss at the source rather than correcting for it at the receiving end. This removes limitations such as time constraints for algorithms that amplify a sound in a…

Discrete representations of speech, obtained from Self-Supervised Learning (SSL) foundation models, are widely used, especially where there are limited data for the downstream task, such as for a low-resource language. Typically,…