Text normalization methods have been commonly applied to historical language or user-
generated content, but less often to dialectal transcriptions. In this paper, we introduce …

The video action segmentation task is regularly explored under weaker forms of supervision,
such as transcript supervision, where a list of actions is easier to obtain than dense frame …

Parallel corpora are ideal for extracting a multilingual named entity (MNE) resource, ie, a
dataset of names translated into multiple languages. Prior work on extracting MNE datasets …

Deep learning Text-to-Speech (TTS) systems have achieved impressive generated speech
quality, close to human parity. However, they suffer from training stability issues and in …

End-to-end (E2E) multi-speaker speech recognition with the serialized output training (SOT)
strategy demonstrates good performance in modeling diverse speaker scenarios. However …

Abstract The Attention-based Encoder–Decoder (AED) models are one of the most popular
models for Automatic Speech Recognition (ASR). However, instability can occur in AED with …

摘要少数民族语言的语音合成有助于民族文化的传承, 保护和发展, 目前相关研究成果较少.
针对不同声调的相同词发音相似时易出现语音合成错误的问题, 提出了一种基于子音节表征的苗 …

In natural language processing, much current research focuses on training larger and larger
models on more and more data. In this thesis, we argue that how data is represented can …