Related papers: Using previous acoustic context to improve Text-to…

In dialog studies, we often encode a dialog using a hierarchical encoder where each utterance is converted into an utterance vector, and then a sequence of utterance vectors is converted into a dialog vector. Since knowing who produced…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Automatic speech recognition (ASR) models are normally trained to operate over single utterances, with a short duration of less than 30 seconds. This choice has been made in part due to computational constraints, but also reflects a common,…

Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…

We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the…

Zero-shot multi-speaker Text-to-Speech (TTS) generates target speaker voices given an input text and the corresponding speaker embedding. In this work, we investigate the effectiveness of the TTS reconstruction objective to improve…

Recent advances in deep learning methods have elevated synthetic speech quality to human level, and the field is now moving towards addressing prosodic variation in synthetic speech.Despite successes in this effort, the state-of-the-art…

Combining the representations of the words that make up a sentence into a cohesive whole is difficult, since it needs to account for the order of words, and to establish how the words present relate to each other. The solution we propose…

Intonations play an important role in delivering the intention of a speaker. However, current end-to-end TTS systems often fail to model proper intonations. To alleviate this problem, we propose a novel, intuitive method to synthesize…

We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual…

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

This paper presents an expressive speech synthesis architecture for modeling and controlling the speaking style at a word level. It attempts to learn word-level stylistic and prosodic representations of the speech data, with the aid of two…

End-to-end models, particularly Tacotron-based ones, are currently a popular solution for text-to-speech synthesis. They allow the production of high-quality synthesized speech with little to no text preprocessing. Indeed, they can be…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

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…

We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.…

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)…

In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy…