English
Related papers

Related papers: Reducing the Offline-Streaming Gap for Unified ASR…

200 papers

This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR). In standard RNN-T, the emission of a blank symbol consumes exactly one input frame; in our proposed method, we introduce additional…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-15 Hainan Xu , Fei Jia , Somshubra Majumdar , Shinji Watanabe , Boris Ginsburg

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

Sound · Computer Science 2021-11-05 Peng Fan , Dongyue Guo , Yi Lin , Bo Yang , Jianwei Zhang

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

User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques for reducing the latency for both components, the automatic…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-24 Thai Son Nguyen , Jan Niehues , Eunah Cho , Thanh-Le Ha , Kevin Kilgour , Markus Muller , Matthias Sperber , Sebastian Stueker , Alex Waibel

Automatic Speech Recognition (ASR) plays a crucial role in voice-based applications. For applications requiring real-time feedback like Voice Search, streaming capability becomes vital. While LSTM/RNN and CTC based ASR systems are commonly…

Sound · Computer Science 2023-05-31 Abhinav Goyal , Nikesh Garera

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Computation and Language · Computer Science 2020-10-28 Suyoun Kim , Yuan Shangguan , Jay Mahadeokar , Antoine Bruguier , Christian Fuegen , Michael L. Seltzer , Duc Le

Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a streaming ASR model achieves higher accuracy but results in…

Sound · Computer Science 2023-09-12 Huaibo Zhao , Yosuke Higuchi , Yusuke Kida , Tetsuji Ogawa , Tetsunori Kobayashi

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

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Our architecture creates sparse computation pathways…

Computation and Language · Computer Science 2022-07-07 Yi Xie , Jonathan Macoskey , Martin Radfar , Feng-Ju Chang , Brian King , Ariya Rastrow , Athanasios Mouchtaris , Grant P. Strimel

In recent years, all-neural end-to-end approaches have obtained state-of-the-art results on several challenging automatic speech recognition (ASR) tasks. However, most existing works focus on building ASR models where train and test data…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-25 Chung-Cheng Chiu , Arun Narayanan , Wei Han , Rohit Prabhavalkar , Yu Zhang , Navdeep Jaitly , Ruoming Pang , Tara N. Sainath , Patrick Nguyen , Liangliang Cao , Yonghui Wu

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-13 Wen Shen Teo , Takafumi Moriya , Masato Mimura

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Kwangyoun Kim , Felix Wu , Prashant Sridhar , Kyu J. Han , Shinji Watanabe

Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integration of streaming…

Computation and Language · Computer Science 2025-06-02 Luong Ho , Khanh Le , Vinh Pham , Bao Nguyen , Tan Tran , Duc Chau

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-11 Nilaksh Das , Sravan Bodapati , Monica Sunkara , Sundararajan Srinivasan , Duen Horng Chau

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…

Computation and Language · Computer Science 2021-02-19 Harsh Shrivastava , Ankush Garg , Yuan Cao , Yu Zhang , Tara Sainath

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

Machine Learning · Computer Science 2024-08-26 Adnan Haider , Xingyu Na , Erik McDermott , Tim Ng , Zhen Huang , Xiaodan Zhuang

In this paper, we explore the benefits of incorporating context into a Recurrent Neural Network (RNN-T) based Automatic Speech Recognition (ASR) model to improve the speech recognition for virtual assistants. Specifically, we use meta…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Swayambhu Nath Ray , Soumyajit Mitra , Raghavendra Bilgi , Sri Garimella

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-01 Peter Vieting , Maximilian Kannen , Benedikt Hilmes , Ralf Schlüter , Hermann Ney

We propose a streaming non-autoregressive (non-AR) decoding algorithm to deliberate the hypothesis alignment of a streaming RNN-T model. Our algorithm facilitates a simple greedy decoding procedure, and at the same time is capable of…

Computation and Language · Computer Science 2022-04-18 Weiran Wang , Ke Hu , Tara N. Sainath