Related papers: Forward-Backward Decoding for Regularizing End-to-…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation,…

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of…

Text simplification (TS) rephrases long sentences into simplified variants while preserving inherent semantics. Traditional sequence-to-sequence models heavily rely on the quantity and quality of parallel sentences, which limits their…

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Deep-learning based methods have shown their advantages in audio coding over traditional ones but limited attention has been paid on real-time communications (RTC). This paper proposes the TFNet, an end-to-end neural speech codec with low…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

In incremental text to speech synthesis (iTTS), the synthesizer produces an audio output before it has access to the entire input sentence. In this paper, we study the behavior of a neural sequence-to-sequence TTS system when used in an…

The encoder-decoder model is widely used in natural language generation tasks. However, the model sometimes suffers from repeated redundant generation, misses important phrases, and includes irrelevant entities. Toward solving these…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the…

We investigate multi-stage pretraining for prosody modeling in diffusion-based TTS. A speaker-conditioned dual-stream encoder is trained with masked language modeling followed by SigLIP-style cross-modal contrastive learning using…

Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The…

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

In neural text-to-speech (TTS), two-stage system or a cascade of separately learned models have shown synthesis quality close to human speech. For example, FastSpeech2 transforms an input text to a mel-spectrogram and then HiFi-GAN…

We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a linguistic decoder, an acoustic synthesizer, and a single attention module that…

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration)…