Related papers: Computational Narrative Understanding for Expressi…
Expressive text-to-speech (TTS) can synthesize a new speaking style by imiating prosody and timbre from a reference audio, which faces the following challenges: (1) The highly dynamic prosody information in the reference audio is difficult…
Expressive Text-to-Speech (TTS) using reference speech has been studied extensively to synthesize natural speech, but there are limitations to obtaining well-represented styles and improving model generalization ability. In this study, we…
Emotion is essential in spoken communication, yet most existing frameworks in speech emotion modeling rely on predefined categories or low-dimensional continuous attributes, which offer limited expressive capacity. Recent advances in speech…
We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-grained prosody transfer between any pair of seen speakers.…
Token-based text-to-speech (TTS) models have emerged as a promising avenue for generating natural and realistic speech, yet they grapple with low pronunciation accuracy, speaking style and timbre inconsistency, and a substantial need for…
For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…
Advances in text-to-speech (TTS) technology have significantly improved the quality of generated speech, closely matching the timbre and intonation of the target speaker. However, due to the inherent complexity of human emotional…
Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch,…
Existing text-to-speech systems predominantly focus on single-sentence synthesis and lack adequate contextual modeling as well as fine-grained performance control capabilities for generating coherent multicast audiobooks. To address these…
Prosodic phrasing is crucial to the naturalness and intelligibility of end-to-end Text-to-Speech (TTS). There exist both linguistic and emotional prosody in natural speech. As the study of prosodic phrasing has been linguistically…
Text-to-speech (TTS) and text-to-music (TTM) models face significant limitations in instruction-based control. TTS systems usually depend on reference audio for timbre, offer only limited text-level attribute control, and rarely support…
Identifying keywords in an open-vocabulary context is crucial for personalizing interactions with smart devices. Previous approaches to open vocabulary keyword spotting dependon a shared embedding space created by audio and text encoders.…
Recent advances in audio-language models have demonstrated remarkable success on short, segment-level speech tasks. However, real-world applications such as meeting transcription, spoken document understanding, and conversational analysis…
Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose…
Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model…
We propose a neural text-to-speech (TTS) model that can imitate a new speaker's voice using only a small amount of speech sample. We demonstrate voice imitation using only a 6-seconds long speech sample without any other information such as…
In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…
This paper links prosody to the information in a text and how it is processed by the speaker. It describes the operation and output of LOQ, a text-to-speech implementation that includes a model of limited attention and working memory.…
How much can we infer about an emotional voice solely from an expressive face? This intriguing question holds great potential for applications such as virtual character dubbing and aiding individuals with expressive language disorders.…
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of…