English
Related papers

Related papers: Conv-Transformer Transducer: Low Latency, Low Fram…

200 papers

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

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Sound · Computer Science 2018-11-07 Santiago Pascual , Antonio Bonafonte , Joan Serrà

We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR) and speaker embedding, obtained from a speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yurii Rebryk , Stanislav Beliaev

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

Computation and Language · Computer Science 2023-07-04 Prateek Verma

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…

Computation and Language · Computer Science 2026-03-13 Youness Dkhissi , Valentin Vielzeuf , Elys Allesiardo , Anthony Larcher

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

The Transformer architecture has been well adopted as a dominant architecture in most sequence transduction tasks including automatic speech recognition (ASR), since its attention mechanism excels in capturing long-range dependencies. While…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-13 Jing Pan , Tao Lei , Kwangyoun Kim , Kyu Han , Shinji Watanabe

Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-21 Tianzi Wang , Yuya Fujita , Xuankai Chang , Shinji Watanabe

Transformer and its variants have shown great potential for various vision tasks in recent years, including image classification, object detection and segmentation. Meanwhile, recent studies also reveal that with proper architecture design,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Xinghao Chen , Siwei Li , Yijing Yang , Yunhe Wang

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks in end-to-end (E2E) automatic speech recognition (ASR) systems. However, Transformer has a drawback in that the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-29 Emiru Tsunoo , Yosuke Kashiwagi , Toshiyuki Kumakura , Shinji Watanabe

Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, increase their cost, and…

Sound · Computer Science 2024-09-12 Titouan Parcollet , Rogier van Dalen , Shucong Zhang , Sourav Batthacharya

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Computation and Language · Computer Science 2020-02-17 Genta Indra Winata , Samuel Cahyawijaya , Zhaojiang Lin , Zihan Liu , Pascale Fung

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

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

As a foundational technology for intelligent human-computer interaction, voice conversion (VC) seeks to transform speech from any source timbre into any target timbre. Traditional voice conversion methods based on Generative Adversarial…

Sound · Computer Science 2025-06-11 Wenhan Yao , Fen Xiao , Xiarun Chen , Jia Liu , YongQiang He , Weiping Wen

Large encoder-decoder models like Whisper achieve strong offline transcription but remain impractical for streaming applications due to high latency. However, due to the accessibility of pre-trained checkpoints, the open Thai ASR landscape…

Transformers have achieved great success in effectively processing sequential data such as text. Their architecture consisting of several attention and feedforward blocks can model relations between elements of a sequence in parallel…

Machine Learning · Computer Science 2025-02-20 Jaemu Heo , Eldor Fozilov , Hyunmin Song , Taehwan Kim

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Qibin Hou , Cheng-Ze Lu , Ming-Ming Cheng , Jiashi Feng

The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Triantafyllos Afouras , Joon Son Chung , Andrew Zisserman