English
Related papers

Related papers: Incremental FastPitch: Chunk-based High Quality Te…

200 papers

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Machine Learning · Computer Science 2025-09-24 Yuxuan Cai , Xiaozhuan Liang , Xinghua Wang , Jin Ma , Haijin Liang , Jinwen Luo , Xinyu Zuo , Lisheng Duan , Yuyang Yin , Xi Chen

We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. This hybrid approach maintains RNN-T's streaming capability…

Machine Learning · Computer Science 2026-03-02 Hainan Xu , Vladimir Bataev , Travis M. Bartley , Jagadeesh Balam

Inspired by a human speech chain mechanism, a machine speech chain framework based on deep learning was recently proposed for the semi-supervised development of automatic speech recognition (ASR) and text-to-speech synthesis TTS) systems.…

Computation and Language · Computer Science 2020-11-05 Sashi Novitasari , Andros Tjandra , Tomoya Yanagita , Sakriani Sakti , Satoshi Nakamura

The recently developed pitch-controllable text-to-speech (TTS) model, i.e. FastPitch, was conditioned for the pitch contours. However, the quality of the synthesized speech degraded considerably for pitch values that deviated significantly…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-13 Hanbin Bae , Young-Sun Joo

End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. And the synthesised speech may also suffer from some error…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-11 Dabiao Ma , Zhiba Su , Wenxuan Wang , Yuhao Lu

Current end-to-end autoregressive TTS systems (e.g. Tacotron 2) have outperformed traditional parallel approaches on the quality of synthesized speech. However, they introduce new problems at the same time. Due to the autoregressive nature,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Yahuan Cong , Ran Zhang , Jian Luan

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Yiwei Guo , Chenpeng Du , Ziyang Ma , Xie Chen , Kai Yu

As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation. The generation of realistic-looking hand-written text…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Alexander Mattick , Martin Mayr , Mathias Seuret , Andreas Maier , Vincent Christlein

Recent progress in large-scale zero-shot speech synthesis has been significantly advanced by language models and diffusion models. However, the generation process of both methods is slow and computationally intensive. Efficient speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-25 Zhen Ye , Zeqian Ju , Haohe Liu , Xu Tan , Jianyi Chen , Yiwen Lu , Peiwen Sun , Jiahao Pan , Weizhen Bian , Shulin He , Wei Xue , Qifeng Liu , Yike Guo

In recent years, speech generation has seen remarkable progress, now achieving one-shot generation capability that is often virtually indistinguishable from real human voice. Integrating such advancements in speech generation with large…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-08 Paweł Budzianowski , Taras Sereda , Tomasz Cichy , Ivan Vulić

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-27 Lauri Juvela , Bajibabu Bollepalli , Junichi Yamagishi , Paavo Alku

Recent advances in text-to-speech (TTS) synthesis, such as Tacotron and WaveRNN, have made it possible to construct a fully neural network based TTS system, by coupling the two components together. Such a system is conceptually simple as it…

Traditional text-to-speech (TTS) methods primarily focus on establishing a mapping between phonemes and mel-spectrograms. However, during the phoneme encoding stage, there is often a lack of real mel-spectrogram auxiliary information, which…

Sound · Computer Science 2025-03-11 Tianyun Liu

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

Computation and Language · Computer Science 2026-03-11 Yen-Ju Lu , Yashesh Gaur , Wei Zhou , Benjamin Muller , Jesus Villalba , Najim Dehak , Luke Zettlemoyer , Gargi Ghosh , Mike Lewis , Srinivasan Iyer , Duc Le

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…

Sound · Computer Science 2023-06-13 Haogeng Liu , Tao Wang , Jie Cao , Ran He , Jianhua Tao

Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex…

Computation and Language · Computer Science 2019-03-19 Gary Wang

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…

Computation and Language · Computer Science 2024-06-26 Yingting Li , Ambuj Mehrish , Bryan Chew , Bo Cheng , Soujanya Poria

Auto-regressive models are widely used in sequence generation problems. The output sequence is typically generated in a predetermined order, one discrete unit (pixel or word or character) at a time. The models are trained by teacher-forcing…

Computation and Language · Computer Science 2019-10-23 Daniel Duckworth , Arvind Neelakantan , Ben Goodrich , Lukasz Kaiser , Samy Bengio

Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-21 Yinghao Aaron Li , Cong Han , Nima Mesgarani

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental…

Computation and Language · Computer Science 2022-07-18 Danni Liu , Changhan Wang , Hongyu Gong , Xutai Ma , Yun Tang , Juan Pino