Related papers: g2pW: A Conditional Weighted Softmax BERT for Poly…

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in…

This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between…

Lip-to-speech (L2S) synthesis for Mandarin is a significant challenge, hindered by complex viseme-to-phoneme mappings and the critical role of lexical tones in intelligibility. To address this issue, we propose Lexical Tone-Aware…

BERT-based models have shown a remarkable ability in the Chinese Spelling Check (CSC) task recently. However, traditional BERT-based methods still suffer from two limitations. First, although previous works have identified that explicit…

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…

Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…

Text-to-Text Transfer Transformer (T5) has recently been considered for the Grapheme-to-Phoneme (G2P) transduction. As a follow-up, a tokenizer-free byte-level model based on T5 referred to as ByT5, recently gave promising results on…

Polyphone disambiguation aims to capture accurate pronunciation knowledge from natural text sequences for reliable Text-to-speech (TTS) systems. However, previous approaches require substantial annotated training data and additional efforts…

As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or…

Word meaning, representation, and interpretation play fundamental roles in natural language understanding (NLU), natural language processing (NLP), and natural language generation (NLG) tasks. Many of the inherent difficulties in these…

Attention mechanism is one of the most successful techniques in deep learning based Natural Language Processing (NLP). The transformer network architecture is completely based on attention mechanisms, and it outperforms sequence-to-sequence…

Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for these Chinese PLMs remain to be the one provided by Google…

Prepositions are frequently occurring polysemous words. Disambiguation of prepositions is crucial in tasks like semantic role labelling, question answering, text entailment, and noun compound paraphrasing. In this paper, we propose a novel…

This paper describes AraS2P, our speech-to-phonemes system submitted to the Iqra'Eval 2025 Shared Task. We adapted Wav2Vec2-BERT via Two-Stage training strategy. In the first stage, task-adaptive continue pretraining was performed on…

Encoder-only Transformers have advanced along three axes -- architecture, data, and systems -- yielding Pareto gains in accuracy, speed, and memory efficiency. Yet these improvements have not fully transferred to Chinese, where tokenization…

Lightweight, real-time text-to-speech systems are crucial for accessibility. However, the most efficient TTS models often rely on lightweight phonemizers that struggle with context-dependent challenges. In contrast, more advanced…

Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language. Building upon…

This paper proposes an additive phoneme-aware margin softmax (APM-Softmax) loss to train the multi-task learning network with phonetic information for language recognition. In additive margin softmax (AM-Softmax) loss, the margin is set as…