This paper introduces a new open source platform for end-toend speech processing named ESPnet. ESPnet mainly focuses on end-to-end automatic speech recognition (ASR), and adopts widely-used dynamic neural network toolkits, Chainer and Py-Torch, as a main deep learning engine. ESPnet also follows the Kaldi ASR toolkit style for data processing, feature extraction/format, and recipes to provide a complete setup for speech recognition and other speech processing experiments. This paper explains a major architecture of this software platform, several important functionalities, which differentiate ESPnet from other open source ASR toolkits, and experimental results with major ASR benchmarks.

Sequence-to-sequence models have been widely used in end-toend speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS benchmarks. Our experiments revealed various training tips and significant performance benefits obtained with Transformer for each task including the surprising superiority of Transformer in 13/15 ASR benchmarks in comparison with RNN. We are preparing to release Kaldi-style reproducible recipes using open source and publicly available datasets for all the ASR, ST, and TTS tasks for the community to succeed our exciting outcomes.

No abstract

In this study, we propose a speaker-dependent WaveNet vocoder, a method of synthesizing speech waveforms with WaveNet, by utilizing acoustic features from existing vocoder as auxiliary features of WaveNet. It is expected that WaveNet can learn a sample-by-sample correspondence between speech waveform and acoustic features. The advantage of the proposed method is that it does not require (1) explicit modeling of excitation signals and (2) various assumptions, which are based on prior knowledge specific to speech. We conducted both subjective and objective evaluation experiments on CMU-ARCTIC database. From the results of the objective evaluation, it was demonstrated that the proposed method could generate high-quality speech with phase information recovered, which was lost by a mel-cepstrum vocoder. From the results of the subjective evaluation, it was demonstrated that the sound quality of the proposed method was significantly improved from mel-cepstrum vocoder, and the proposed method could capture source excitation information more accurately.

No abstract

No abstract

We present ESPnet-ST, which is designed for the quick development of speech-to-speech translation systems in a single framework. ESPnet-ST is a new project inside end-toend speech processing toolkit, ESPnet, which integrates or newly implements automatic speech recognition, machine translation, and text-to-speech functions for speech translation. We provide all-in-one recipes including data pre-processing, feature extraction, training, and decoding pipelines for a wide range of benchmark datasets. Our reproducible results can match or even outperform the current state-of-the-art performances; these pretrained models are downloadable. The toolkit is publicly available at https://github. com/espnet/espnet.

Covalent organic frameworks (COFs) are an emerging class of crystalline porous polymers in which organic building blocks are covalently and topologically linked to form extended crystalline polygon structures, constituting a new platform for designing π-electronic porous materials. However, COFs are currently synthesised by a few chemical reactions, limiting the access to and exploration of new structures and properties. The development of new reaction systems that avoid such limitations to expand structural diversity is highly desired. Here we report that COFs can be synthesised via a double-stage connection that polymerises various different building blocks into crystalline polygon architectures, leading to the development of a new type of COFs with enhanced structural complexity and diversity. We show that the double-stage approach not only controls the sequence of building blocks but also allows fine engineering of pore size and shape. This strategy is widely applicable to different polymerisation systems to yield hexagonal, tetragonal and rhombus COFs with predesigned pores and π-arrays.