Related papers: Back-Translation-Style Data Augmentation for Manda…
Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese texts. Although efforts have been made to introduce phonetic information (Hanyu Pinyin) in this task, they typically merge phonetic representations…
An increasing number of Chinese people are troubled by different degrees of visual impairment, which has made the modal conversion between a single image or video frame in the visual field and the audio expressing the same information a…
A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very…
Autoformalization, the process of transforming informal mathematical language into formal specifications and proofs remains a difficult task for state-of-the-art (large) language models. Existing works point to competing explanations for…
Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without…
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the…
Large Language Models (LLMs) have gained significant attention in the field of natural language processing (NLP) due to their wide range of applications. However, training LLMs for languages other than English poses significant challenges,…
This study investigates whether phonological features can be applied in text-to-speech systems to generate native and non-native speech in English and Mandarin. We present a mapping of ARPABET/pinyin to SAMPA/SAMPA-SC and then to…
In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing…
Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per…
This paper explores predicting suitable prosodic features for fine-grained emotion analysis from the discourse-level text. To obtain fine-grained emotional prosodic features as predictive values for our model, we extract a phoneme-level…
Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system…
We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa…
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT,…
The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learning and data augmentation to alleviate this issue. We study…
Although end-to-end text-to-speech (TTS) models can generate natural speech, challenges still remain when it comes to estimating sentence-level phonetic and prosodic information from raw text in Japanese TTS systems. In this paper, we…
Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into…
Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings. In this paper, we argue that Chinese word embeddings can be substantially enriched by the morphological information hidden in…