Related papers: VALL-E 2: Neural Codec Language Models are Human P…

We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover…

We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Code-Switching (CS) is referred to the phenomenon of alternately using words and phrases from different languages. While today's neural end-to-end (E2E) models deliver state-of-the-art performances on the task of automatic speech…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance…

We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for…

Recent approaches have shown impressive proficiency in extracting and leveraging parametric knowledge from Large-Language Models (LLMs) and Vision-Language Models (VLMs). In this work, we consider how we can improve the identification and…

Recently, the effectiveness of text-to-speech (TTS) systems combined with neural vocoders to generate high-fidelity speech has been shown. However, collecting the required training data and building these advanced systems from scratch are…

While FastSpeech2 aims to integrate aspects of speech such as pitch, energy, and duration as conditional inputs, it still leaves scope for richer representations. As a part of this work, we leverage representations from various…

Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor languages dominant in the training data and consequently…

This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are…

Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image…

Non-parallel voice conversion (VC) is a technique for learning the mapping from source to target speech without relying on parallel data. This is an important task, but it has been challenging due to the disadvantages of the training…

This paper describes ESPnet2-TTS, an end-to-end text-to-speech (E2E-TTS) toolkit. ESPnet2-TTS extends our earlier version, ESPnet-TTS, by adding many new features, including: on-the-fly flexible pre-processing, joint training with neural…

In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic content from speaker-specific details. We propose two neural…

While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content,…

We introduce SupertonicTTS, a novel text-to-speech (TTS) system designed for efficient and streamlined speech synthesis. SupertonicTTS comprises three components: a speech autoencoder for continuous latent representation, a text-to-latent…

Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…