5 accepted papers
In this paper, we take a step towards jointly modeling automatic speech recognition (STT) and speech synthesis (TTS) in a fully non-autoregressive way. We develop a novel multimodal framework capable of handling the speech and text modalities as input either individually or together. The proposed mo…
Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is impractical for fluent voice conversations. We propose LLM2Speech, an…
Autoregressive Attentive Sequence-to-Sequence (S2S) speech synthesis is considered state-of-the-art in terms of speech quality and naturalness, as evaluated on a finite set of testing utterances. However, it can occasionally suffer from stability issues at inference time, such as local intelligibili…
Controllable generation of emphasis in speech is desirable for expressive TTS systems utilized in various dialog applications. Usually such models remain voice-specific and the strength of emphasis can't be readily controlled. In this work we present a flexible emphatic prosody generation model base…
In expressive TTS and voice transformation systems, implantation of expressive prosody derived from external out-of-domain sources often leads to extreme pitch modification that compromises the naturalness of the synthesized speech. In this work we investigate and prove a hypothesis that the natural…