English
Related papers

Related papers: Globally Normalising the Transducer for Streaming …

200 papers

Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was…

Machine Learning · Computer Science 2025-12-17 Chaohao Yuan , Zhenjie Song , Ercan Engin Kuruoglu , Kangfei Zhao , Yang Liu , Deli Zhao , Hong Cheng , Yu Rong

After a neural sequence model encounters an unexpected token, can its behavior be predicted? We show that RNN and transformer language models exhibit structured, consistent generalization in out-of-distribution contexts. We begin by…

Computation and Language · Computer Science 2021-11-08 Anthony Bau , Jacob Andreas

We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-16 Andreas Schwarz , Ilya Sklyar , Simon Wiesler

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future…

Audio and Speech Processing · Electrical Eng. & Systems 2018-06-13 Mirco Ravanelli , Dmitriy Serdyuk , Yoshua Bengio

Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network. In this paper we propose qualitative modifications to the model…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-14 Enrico Fini , Alessio Brutti

This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-13 Takaki Makino , Hank Liao , Yannis Assael , Brendan Shillingford , Basilio Garcia , Otavio Braga , Olivier Siohan

Call a string-to-string transducer regular if it can be realised by one of the following equivalent models: mso transductions, two-way deterministic automata with output, and streaming transducers with registers. This paper proposes to…

Formal Languages and Automata Theory · Computer Science 2013-09-25 Mikołaj Bojańczyk

The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-10 Takuya Yoshioka , Hakan Erdogan , Zhuo Chen , Xiong Xiao , Fil Alleva

Real-noise denoising is a challenging task because the statistics of real-noise do not follow the normal distribution, and they are also spatially and temporally changing. In order to cope with various and complex real-noise, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Yoonsik Kim , Jae Woong Soh , Gu Yong Park , Nam Ik Cho

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…

Computation and Language · Computer Science 2023-10-27 Biao Fu , Minpeng Liao , Kai Fan , Zhongqiang Huang , Boxing Chen , Yidong Chen , Xiaodong Shi

Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the…

Computation and Language · Computer Science 2019-11-21 Yi Ren , Yangjun Ruan , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , Tie-Yan Liu

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Sound · Computer Science 2023-12-06 Pavel Andreev , Nicholas Babaev , Azat Saginbaev , Ivan Shchekotov , Aibek Alanov

Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language. TL can be applied to end-to-end (E2E) ASR system such as recurrent neural…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-18 Vikas Joshi , Rui Zhao , Rupesh R. Mehta , Kshitiz Kumar , Jinyu Li

Confidence estimate is an often requested feature in applications such as medical transcription where errors can impact patient care and the confidence estimate could be used to alert medical professionals to verify potential errors in…

Computation and Language · Computer Science 2021-10-29 Mingqiu Wang , Hagen Soltau , Laurent El Shafey , Izhak Shafran

The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…

Computation and Language · Computer Science 2023-03-14 Stefan Braun , Erik McDermott , Roger Hsiao

RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-30 Dario Albesano , Jesús Andrés-Ferrer , Nicola Ferri , Puming Zhan

The growing need for instant spoken language transcription and translation is driven by increased global communication and cross-lingual interactions. This has made offering translations in multiple languages essential for user…

Computation and Language · Computer Science 2023-10-24 Sara Papi , Peidong Wang , Junkun Chen , Jian Xue , Naoyuki Kanda , Jinyu Li , Yashesh Gaur

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

Machine Learning · Computer Science 2024-05-15 Mingbin Xu , Alex Jin , Sicheng Wang , Mu Su , Tim Ng , Henry Mason , Shiyi Han , Zhihong Lei , Yaqiao Deng , Zhen Huang , Mahesh Krishnamoorthy

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…

Computation and Language · Computer Science 2021-01-25 Orion Weller , Matthias Sperber , Christian Gollan , Joris Kluivers

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Machine Learning · Computer Science 2021-08-19 Radostin Cholakov , Todor Kolev