English
Related papers

Related papers: Combining Masked Language Modeling and Cross-Modal…

200 papers

Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…

Sound · Computer Science 2021-06-14 Jaehyeon Kim , Jungil Kong , Juhee Son

Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks.…

Sound · Computer Science 2025-08-18 Kentaro Onda , Satoru Fukayama , Daisuke Saito , Nobuaki Minematsu

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…

Sound · Computer Science 2021-07-05 Tao Han , Hantao Huang , Ziang Yang , Wei Han

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…

Sound · Computer Science 2025-10-01 Kang Yang , Yifan Liang , Fangkun Liu , Zhenping Xie , Chengshi Zheng

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…

Multimedia · Computer Science 2022-12-02 Xiaohuan Zhou , Jiaming Wang , Zeyu Cui , Shiliang Zhang , Zhijie Yan , Jingren Zhou , Chang Zhou

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Xuehao Zhou , Mingyang Zhang , Yi Zhou , Zhizheng Wu , Haizhou Li

Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language.…

Computation and Language · Computer Science 2021-04-08 Aparna Khare , Srinivas Parthasarathy , Shiva Sundaram

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Sound · Computer Science 2024-04-02 Xiang Li , Fan Bu , Ambuj Mehrish , Yingting Li , Jiale Han , Bo Cheng , Soujanya Poria

Vision-language models pre-trained on large scale of unlabeled biomedical images and associated reports learn generalizable semantic representations. These multi-modal representations can benefit various downstream tasks in the biomedical…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Xinliu Zhong , Kayhan Batmanghelich , Li Sun

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high…

Computer Vision and Pattern Recognition · Computer Science 2022-05-23 Haoyu Lu , Nanyi Fei , Yuqi Huo , Yizhao Gao , Zhiwu Lu , Ji-Rong Wen

The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS. However, its predicting capability is still limited by the acoustic/phonetic…

Computation and Language · Computer Science 2019-04-10 Haohan Guo , Frank K. Soong , Lei He , Lei Xie

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for…

Sound · Computer Science 2022-11-28 Zhuoyuan Yao , Shuo Ren , Sanyuan Chen , Ziyang Ma , Pengcheng Guo , Lei Xie

Most existing masked audio modeling (MAM) methods learn audio representations by masking and reconstructing local spectrogram patches. However, the reconstruction loss mainly accounts for the signal-level quality of the reconstructed…

Sound · Computer Science 2024-01-30 Yifei Xin , Xiulian Peng , Yan Lu

Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and…

Computation and Language · Computer Science 2021-04-22 Ozan Caglayan , Menekse Kuyu , Mustafa Sercan Amac , Pranava Madhyastha , Erkut Erdem , Aykut Erdem , Lucia Specia

Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-04 Yan Deng , Lei He , Frank Soong

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

Computation and Language · Computer Science 2022-09-21 Yiren Jian , Chongyang Gao , Soroush Vosoughi

Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…

Computation and Language · Computer Science 2022-03-03 Wentao Zhang , Shuang Xu , Haoran Huang

Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice styles and emotions is notoriously difficult and typically…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-13 Zhicheng Ouyang , Seong-Gyun Leem , Bach Viet Do , Haibin Wu , Ariya Rastrow , Yuzong Liu , Florian Metze

We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of intrinsic (speaker-level) and situational (utterance-level) descriptors (such…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-31 Anuj Diwan , Eunsol Choi , David Harwath

Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks. These models usually aggregate uni-modal local representations, namely frame or word features,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-16 Yiming Li , Zhifang Guo , Xiangdong Wang , Hong Liu