Related papers: AttS2S-VC: Sequence-to-Sequence Voice Conversion w…

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

This thesis introduces the sequence to sequence model with Luong's attention mechanism for end-to-end ASR. It also describes various neural network algorithms including Batch normalization, Dropout and Residual network which constitute the…

Currently, there are increasing interests in text-to-speech (TTS) synthesis to use sequence-to-sequence models with attention. These models are end-to-end meaning that they learn both co-articulation and duration properties directly from…

Generating audio from a video's visual context has multiple practical applications in improving how we interact with audio-visual media - for example, enhancing CCTV footage analysis, restoring historical videos (e.g., silent movies), and…

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…

A chatbot is an intelligent software application that automates conversations and engages users in natural language through messaging platforms. Leveraging artificial intelligence (AI), chatbots serve various functions, including customer…

Vector representation of sentences is important for many text processing tasks that involve clustering, classifying, or ranking sentences. Recently, distributed representation of sentences learned by neural models from unlabeled data has…

The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural network. In natural language processing,…

Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that…

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently…

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long…

The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to extract disentangled linguistic content from the source and…

Text normalization, or the process of transforming text into a consistent, canonical form, is crucial for speech applications such as text-to-speech synthesis (TTS). In TTS, the system must decide whether to verbalize "1995" as "nineteen…

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by…

Speech representation learning with self-supervised algorithms has resulted in notable performance boosts in many downstream tasks. Recent work combined self-supervised learning (SSL) and visually grounded speech (VGS) processing mechanisms…

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

We describe a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during…

With recent advancements in voice cloning, the performance of speech synthesis for a target speaker has been rendered similar to the human level. However, autoregressive voice cloning systems still suffer from text alignment failures,…

Current self-supervised learning algorithms are often modality-specific and require large amounts of computational resources. To address these issues, we increase the training efficiency of data2vec, a learning objective that generalizes…