English
Related papers

Related papers: ToneUnit: A Speech Discretization Approach for Ton…

200 papers

We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for multilingual speech recognition and synthesis. Prior work has predominantly used characters, sub-words or words as the unit of choice to model text. These…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-27 Bo Li , Yu Zhang , Tara Sainath , Yonghui Wu , William Chan

In this paper, we present a new method for recognizing tones in continuous speech for tonal languages. The method works by converting the speech signal to a cepstrogram, extracting a sequence of cepstral features using a convolutional…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-09 Loren Lugosch , Vikrant Singh Tomar

For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for…

Tonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different…

Computation and Language · Computer Science 2026-01-15 Tianyi Xu , Xuan Ouyang , Binwei Yao , Shoua Xiong , Sara Misurelli , Maichou Lor , Junjie Hu

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and…

Sound · Computer Science 2022-09-23 Rui Liu , Berrak Sisman , Guanglai Gao , Haizhou Li

Recent advancements in generative artificial intelligence have significantly transformed the field of style-captioned text-to-speech synthesis (CapTTS). However, adapting CapTTS to real-world applications remains challenging due to the lack…

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…

Computation and Language · Computer Science 2018-10-04 Sergey Edunov , Myle Ott , Michael Auli , David Grangier

We introduce StyleFusion-TTS, a prompt and/or audio referenced, style and speaker-controllable, zero-shot text-to-speech (TTS) synthesis system designed to enhance the editability and naturalness of current research literature. We propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Zhiyong Chen , Xinnuo Li , Zhiqi Ai , Shugong Xu

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Computation and Language · Computer Science 2025-10-30 Shreyas Gopal , Ashutosh Anshul , Haoyang Li , Yue Heng Yeo , Hexin Liu , Eng Siong Chng

The Chinese pronunciation system offers two characteristics that distinguish it from other languages: deep phonemic orthography and intonation variations. We are the first to argue that these two important properties can play a major role…

Computation and Language · Computer Science 2019-01-24 Haiyun Peng , Yukun Ma , Soujanya Poria , Yang Li , Erik Cambria

A patent is a property right for an invention granted by the government to the inventor. An invention is a solution to a specific technological problem. So patents often have a high concentration of scientific and technical terms that are…

Computation and Language · Computer Science 2016-12-01 Si Li , Nianwen Xue

In Standard Chinese, Tone 3 (the dipping tone) becomes Tone 2 (rising tone) when followed by another Tone 3. Previous studies have noted that this sandhi process may be incomplete, in the sense that the assimilated Tone 3 is still distinct…

Computation and Language · Computer Science 2026-03-18 Yuxin Lu , Yu-Ying Chuang , R. Harald Baayen

How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and Language Model…

Computation and Language · Computer Science 2023-06-16 Ziqiang Zhang , Sanyuan Chen , Long Zhou , Yu Wu , Shuo Ren , Shujie Liu , Zhuoyuan Yao , Xun Gong , Lirong Dai , Jinyu Li , Furu Wei

End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-27 Jianwei Sun , Zhiyuan Tang , Hengxin Yin , Wei Wang , Xi Zhao , Shuaijiang Zhao , Xiaoning Lei , Wei Zou , Xiangang Li

Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected. In this paper, we propose QI-TTS which aims to better transfer and control intonation to…

Sound · Computer Science 2023-03-15 Haobin Tang , Xulong Zhang , Jianzong Wang , Ning Cheng , Jing Xiao

This paper investigates a method for simulating natural conversation in the model training of end-to-end neural diarization (EEND). Due to the lack of any annotated real conversational dataset, EEND is usually pretrained on a large-scale…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-26 Natsuo Yamashita , Shota Horiguchi , Takeshi Homma

In order to obtain a model which can process sequential data related to machine translation and speech recognition faster and more accurately, we propose adopting Chrono Initializer as the initialization method of Minimal Gated Unit. We…

Machine Learning · Computer Science 2019-06-04 Kazuki Takamura , Satoshi Yamane

In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model…

Computation and Language · Computer Science 2023-05-30 Hongqiu Wu , Shaohua Zhang , Yuchen Zhang , Hai Zhao

We propose a system to develop a basic automatic speech recognizer(ASR) for Cantonese, a low-resource language, through transfer learning of Mandarin, a high-resource language. We take a time-delayed neural network trained on Mandarin, and…

Computation and Language · Computer Science 2019-11-22 Bryan Li , Xinyue Wang , Homayoon Beigi

Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored…