Related papers: Pruning Self-Attention for Zero-Shot Multi-Speaker…
Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose Spotlight-TTS,…
Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that…
This paper introduces StyleSpeech, a novel Text-to-Speech~(TTS) system that enhances the naturalness and accuracy of synthesized speech. Building upon existing TTS technologies, StyleSpeech incorporates a unique Style Decorator structure…
Recently, end-to-end speech translation (ST) has gained significant attention as it avoids error propagation. However, the approach suffers from data scarcity. It heavily depends on direct ST data and is less efficient in making use of…
Zero-shot Text-to-Speech (TTS) models can generate speech that captures both the voice timbre and accent of a reference speaker. However, disentangling these attributes remains challenging, as the output often inherits both the accent and…
This study aims at designing an environment-aware text-to-speech (TTS) system that can generate speech to suit specific acoustic environments. It is also motivated by the desire to leverage massive data of speech audio from heterogeneous…
We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively using transcripts from a single speaker. ParrotTTS adapts to…
Style transfer for out-of-domain (OOD) speech synthesis aims to generate speech samples with unseen style (e.g., speaker identity, emotion, and prosody) derived from an acoustic reference, while facing the following challenges: 1) The…
Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies…
With rapid globalization, the need to build inclusive and representative speech technology cannot be overstated. Accent is an important aspect of speech that needs to be taken into consideration while building inclusive speech synthesizers.…
We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is…
The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize. However, this important aspect is often…
Target speech extraction is a technique to extract the target speaker's voice from mixture signals using a pre-recorded enrollment utterance that characterize the voice characteristics of the target speaker. One major difficulty of target…
While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available,…
Large language models (LLMs) face significant deployment challenges due to their massive computational demands. % While pruning offers a promising compression solution, existing methods suffer from two critical limitations: (1) They neglect…
Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority…
Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them for new speakers or languages is not straightforward in a low-resource setup. In this paper, we show…
This paper presents a novel design of neural network system for fine-grained style modeling, transfer and prediction in expressive text-to-speech (TTS) synthesis. Fine-grained modeling is realized by extracting style embeddings from the…
Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with simpler sequential modules is appealing, yet naive…
How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…