English
Related papers

Related papers: RelayS2S: A Dual-Path Speculative Generation for R…

200 papers

Recent advances of end-to-end models have outperformed conventional models through employing a two-pass model. The two-pass model provides better speed-quality trade-offs for on-device speech recognition, where a 1st-pass model generates…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-24 Wei Li , James Qin , Chung-Cheng Chiu , Ruoming Pang , Yanzhang He

End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-19 Ke Hu , Tara N. Sainath , Ruoming Pang , Rohit Prabhavalkar

Grammatical Error Correction (GEC) and feedback play a vital role in supporting second language (L2) learners, educators, and examiners. While written GEC is well-established, spoken GEC (SGEC), aiming to provide feedback based on learners'…

Computation and Language · Computer Science 2025-06-25 Mengjie Qian , Rao Ma , Stefano Bannò , Mark J. F. Gales , Kate M. Knill

Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-15 Yi Ren , Jinglin Liu , Zhou Zhao

Designing distributed, fast and reliable wireless consensus protocols is instrumental in enabling mission-critical decentralized systems, such as robotic networks in the industrial Internet of Things (IIoT), drone swarms in rescue missions,…

Information Theory · Computer Science 2020-05-26 Hyowoon Seo , Jihong Park , Mehdi Bennis , Wan Choi

Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions are polarized between "trigger-happy" VAD-based methods that…

Sound · Computer Science 2026-03-26 Kangxiang Xia , Bingshen Mu , Xian Shi , Jin Xu , Lei Xie

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Takafumi Moriya , Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Takahiro Shinozaki

Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming…

Sound · Computer Science 2025-06-17 Hui Wang , Yifan Yang , Shujie Liu , Jinyu Li , Lingwei Meng , Yanqing Liu , Jiaming Zhou , Haoqin Sun , Yan Lu , Yong Qin

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

Computation and Language · Computer Science 2025-09-30 Jiazheng Li , Yuxiang Zhou , Junru Lu , Gladys Tyen , Lin Gui , Cesare Aloisi , Yulan He

In this paper, we propose a novel system that integrates state-of-the-art, domain-specific large language models with advanced information retrieval techniques to deliver comprehensive and context-aware responses. Our approach facilitates…

Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive…

Sound · Computer Science 2024-10-02 Trung Dang , David Aponte , Dung Tran , Tianyi Chen , Kazuhito Koishida

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and…

Sound · Computer Science 2021-02-09 Renqian Luo , Xu Tan , Rui Wang , Tao Qin , Jinzhu Li , Sheng Zhao , Enhong Chen , Tie-Yan Liu

Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or less independently without exerting much mutual influence on…

Computation and Language · Computer Science 2017-07-18 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-05 Zhen Zeng , Jianzong Wang , Ning Cheng , Tian Xia , Jing Xiao

This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current…

Computation and Language · Computer Science 2023-09-21 Xinyu Zhou , Delong Chen , Yudong Chen

We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic…

Computation and Language · Computer Science 2017-12-01 Yu Wu , Wei Wu , Dejian Yang , Can Xu , Zhoujun Li , Ming Zhou

The timings of spoken response offsets in human dialogue have been shown to vary based on contextual elements of the dialogue. We propose neural models that simulate the distributions of these response offsets, taking into account the…

Computation and Language · Computer Science 2020-05-20 Matthew Roddy , Naomi Harte

The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous…

Sound · Computer Science 2024-02-01 Wenhao Guan , Qi Su , Haodong Zhou , Shiyu Miao , Xingjia Xie , Lin Li , Qingyang Hong

Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of-thought (CoT) reasoning even for simple inputs and…

Computation and Language · Computer Science 2026-01-09 Feng Luo , Yu-Neng Chuang , Guanchu Wang , Hoang Anh Duy Le , Shaochen Zhong , Hongyi Liu , Jiayi Yuan , Yang Sui , Vladimir Braverman , Vipin Chaudhary , Xia Hu

Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupling semantic-token ASR with a two-stage TTS: an…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-05 Mingxuan Wang , Satoshi Nakamura