相关论文: ToneUnit: A Speech Discretization Approach for Ton…

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…

Discrete speech units (DSUs) are derived by quantising representations from models trained using self-supervised learning (SSL). They are a popular representation for a wide variety of spoken language tasks, including those where prosody…

Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech language models from performing instruction-based free-form…

Tone is a crucial component of the prosody of Shanghainese, a Wu Chinese variety spoken primarily in urban Shanghai. Tone sandhi, which applies to all multi-syllabic words in Shanghainese, then, is key to natural-sounding speech.…

Chinese dialects are different variations of Chinese and can be considered as different languages in the same language family with Mandarin. Though they all use Chinese characters, the pronunciations, grammar and idioms can vary…

Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…

This study reports our efforts to improve automatic recognition of suprasegmentals by fine-tuning wav2vec 2.0 with CTC, a method that has been successful in automatic speech recognition. We demonstrate that the method can improve the…

Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of…

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens…

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic…

Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented. In this work, we use unsupervised representation learning to identify probable clusters of syllables that share…

The study explored a new technique of phonetic tone training, which may have a positive impact on second language learning and tone training.

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint…

In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech. Building a typical pipeline-based front-end which consists of multiple…

The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing…

Sentence Simplification is a valuable technique that can benefit language learners and children a lot. However, current research focuses more on English sentence simplification. The development of Chinese sentence simplification is…

Lexical tones play a crucial role in Sino-Tibetan languages. However, current phonetic fieldwork relies on manual effort, resulting in substantial time and financial costs. This is especially challenging for the numerous endangered…

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…

The aim of this project was to develop and implement an English language Text-to-Speech synthesis system. This involved a study of mechanisms of human speech production, a review of techniques in speech synthesis, and analysis of tests used…