English
Related papers

Related papers: Continuous-Token Diffusion for Speaker-Referenced …

200 papers

Diffusion language models have emerged as a promising approach for text generation. One would naturally expect this method to be an efficient replacement for autoregressive models since multiple tokens can be sampled in parallel during each…

Machine Learning · Computer Science 2025-06-10 Guhao Feng , Yihan Geng , Jian Guan , Wei Wu , Liwei Wang , Di He

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

Diffusion and flow matching TTS faces a tension between discrete temporal structure and continuous spectral modeling. Two-stage models diffuse on fixed alignments, often collapsing to mean prosody; single-stage models avoid explicit…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-17 Jiabao Ai , Minghui Zhao , Anton Ragni

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Computation and Language · Computer Science 2026-05-11 Viacheslav Meshchaninov , Alexander Shabalin , Egor Chimbulatov , Nikita Gushchin , Ilya Koziev , Alexander Korotin , Dmitry Vetrov

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Machine Learning · Computer Science 2026-04-08 Jay Mohta , Kenan Emir Ak , Gwang Lee , Dimitrios Dimitriadis , Yan Xu , Mingwei Shen

Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent in their…

Machine Learning · Computer Science 2026-04-28 Anej Svete , Ashish Sabharwal

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Zehan Li , Yan Yang , Xueqing Li , Jian Kang , Xiao-Lei Zhang , Jie Li

Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech…

Computation and Language · Computer Science 2026-04-30 Davyd Naveriani , Albert Zeyer , Ralf Schlüter , Hermann Ney

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

Sound · Computer Science 2026-01-28 Tianhua Li , Chenda Li , Wei Wang , Xin Zhou , Xihui Chen , Jianqing Gao , Yanmin Qian

Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs demonstrate remarkable versatility, MLLMs appears limited…

Computation and Language · Computer Science 2025-03-07 Wenke Huang , Jian Liang , Xianda Guo , Yiyang Fang , Guancheng Wan , Xuankun Rong , Chi Wen , Zekun Shi , Qingyun Li , Didi Zhu , Yanbiao Ma , Ke Liang , Bin Yang , He Li , Jiawei Shao , Mang Ye , Bo Du

The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Deepanway Ghosal , Navonil Majumder , Ambuj Mehrish , Soujanya Poria

Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into…

Extending pre-trained text Large Language Models (LLMs)'s speech understanding or generation abilities by introducing various effective speech tokens has attracted great attention in the speech community. However, building a unified speech…

Sound · Computer Science 2025-11-18 Yuanyuan Wang , Dongchao Yang , Yiwen Shao , Hangting Chen , Jiankun Zhao , Zhiyong Wu , Helen Meng , Xixin Wu

Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL)…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-13 Yifan Liang , Andong Li , Kang Yang , Guochen Yu , Fangkun Liu , Lingling Dai , Xiaodong Li , Chengshi Zheng

Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference.…

Computation and Language · Computer Science 2023-09-20 Atli Thor Sigurgeirsson , Simon King

Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability…

This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron…

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…

Computation and Language · Computer Science 2025-05-27 Richard He Bai , Zijin Gu , Tatiana Likhomanenko , Navdeep Jaitly

Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbone networks for speaker embedding are designed to aggregate…

Sound · Computer Science 2022-03-18 Ruiteng Zhang , Jianguo Wei , Xugang Lu , Wenhuan Lu , Di Jin , Junhai Xu , Lin Zhang , Yantao Ji , Jianwu Dang