English
Related papers

Related papers: SoundWeaver: Semantic Warm-Starting for Text-to-Au…

200 papers

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due to its discrete…

Computation and Language · Computer Science 2024-02-22 Rabeeh Karimi Mahabadi , Hamish Ivison , Jaesung Tae , James Henderson , Iz Beltagy , Matthew E. Peters , Arman Cohan

Explaining the decisions made by audio spoofing detection models is crucial for fostering trust in detection outcomes. However, current research on the interpretability of detection models is limited to applying XAI tools to post-trained…

Sound · Computer Science 2025-07-28 Menglu Li , Xiao-Ping Zhang

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-09 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Dongjune Lee , Nam Soo Kim

We introduce DIVE, an end-to-end speaker diarization algorithm. Our neural algorithm presents the diarization task as an iterative process: it repeatedly builds a representation for each speaker before predicting the voice activity of each…

Sound · Computer Science 2021-05-31 Neil Zeghidour , Olivier Teboul , David Grangier

In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-03 Helin Wang , Jiarui Hai , Yen-Ju Lu , Karan Thakkar , Mounya Elhilali , Najim Dehak

This research addresses the challenge of developing speech applications for zero-resource languages that lack labelled data. It specifically uses acoustic word embedding (AWE) -- fixed-dimensional representations of variable-duration speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-24 Christiaan Jacobs

Millimeter wave (mmWave) based speech recognition provides more possibility for audio-related applications, such as conference speech transcription and eavesdropping. However, considering the practicality in real scenarios, latency and…

Sound · Computer Science 2023-08-17 Running Zhao , Jiangtao Yu , Hang Zhao , Edith C. H. Ngai

We present OmniVoice, a massively multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional…

Computation and Language · Computer Science 2026-04-22 Han Zhu , Lingxuan Ye , Wei Kang , Zengwei Yao , Liyong Guo , Fangjun Kuang , Zhifeng Han , Weiji Zhuang , Long Lin , Daniel Povey

In this paper, we are interested in unsupervised (unknown noise) audio-visual speech enhancement based on variational autoencoders (VAEs), where the probability distribution of clean speech spectra is simulated using an encoder-decoder…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-10 Mostafa Sadeghi , Xavier Alameda-Pineda

Diffusion models have shown exceptional scaling properties in the image synthesis domain, and initial attempts have shown similar benefits for applying diffusion to unconditional text synthesis. Denoising diffusion models attempt to…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-17 Matthew Baas , Kevin Eloff , Herman Kamper

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-07 Puyuan Peng , Herman Kamper , Karen Livescu

We present a lightweight latent diffusion model for vocal-conditioned musical accompaniment generation that addresses critical limitations in existing music AI systems. Our approach introduces a novel soft alignment attention mechanism that…

Sound · Computer Science 2026-01-06 Hei Shing Cheung , Boya Zhang , Jonathan H. Chan

End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their impressive performance, such models have difficulty disambiguating the pronunciations of identically…

Sound · Computer Science 2022-07-29 Artem Ploujnikov , Mirco Ravanelli

Spotting user-defined/flexible keywords represented in text frequently uses an expensive text encoder for joint analysis with an audio encoder in an embedding space, which can suffer from heterogeneous modality representation (i.e., large…

Sound · Computer Science 2023-08-15 Kumari Nishu , Minsik Cho , Paul Dixon , Devang Naik

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-21 Tsun-An Hsieh , Sebastian Braun

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Shentong Mo , Jing Shi , Yapeng Tian

We present LongCat-AudioDiT, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as…

Sound · Computer Science 2026-04-01 Detai Xin , Shujie Hu , Chengzuo Yang , Chen Huang , Guoqiao Yu , Guanglu Wan , Xunliang Cai

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without…

Sound · Computer Science 2024-06-17 Dongchao Yang , Dingdong Wang , Haohan Guo , Xueyuan Chen , Xixin Wu , Helen Meng

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…

Computation and Language · Computer Science 2026-03-23 Zhengpei Hu , Kai Li , Dapeng Fu , Chang Zeng , Yue Li , Yuanhao Tang , Jianqiang Huang

Semantic communication, due to its focus on the transmitting meaning rather than the raw bit data, poses unique security challenges compared to the traditional communication systems. In particular, semantic communication systems are…

Information Theory · Computer Science 2025-05-12 Boxiang He , Zihan Chen , Junshan Luo , Chuanhong Liu , Shilian Wang , Fanggang Wang , Tony Q. S. Quek