English
Related papers

Related papers: Align-Refine: Non-Autoregressive Speech Recognitio…

200 papers

Neural end-to-end (E2E) models have become a promising technique to realize practical automatic speech recognition (ASR) systems. When realizing such a system, one important issue is the segmentation of audio to deal with streaming input or…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-19 Yuya Fujita , Tianzi Wang , Shinji Watanabe , Motoi Omachi

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

Computation and Language · Computer Science 2017-02-02 Suyoun Kim , Takaaki Hori , Shinji Watanabe

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Sound · Computer Science 2026-03-12 Sofiene Kammoun , Xavier Alameda-Pineda , Simon Leglaive

Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…

Computation and Language · Computer Science 2024-10-15 Shen-sian Syu , Juncheng Xie , Hung-yi Lee

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-20 Mohammad Reza Peyghan , Saman Soleimani Roudi , Saeedreza Zouashkiani , Sajjad Amini , Fatemeh Rajabi , Shahrokh Ghaemmaghami

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…

Sound · Computer Science 2020-11-19 Kun Wei , Pengcheng Guo , Hang Lv , Zhen Tu , Lei Xie

Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to…

Computation and Language · Computer Science 2020-12-17 Qiu Ran , Yankai Lin , Peng Li , Jie Zhou

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

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Shantanu Jaiswal , Mihir Prabhudesai , Nikash Bhardwaj , Zheyang Qin , Amir Zadeh , Chuan Li , Katerina Fragkiadaki , Deepak Pathak

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-09 Da-Hee Yang , Joon-Hyuk Chang

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

Neural and Evolutionary Computing · Computer Science 2018-06-04 Shuai Tang , Hailin Jin , Chen Fang , Zhaowen Wang , Virginia R. de Sa

Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text-only data, language model (LM) integration approaches such…

Computation and Language · Computer Science 2022-09-12 Hayato Futami , Hirofumi Inaguma , Sei Ueno , Masato Mimura , Shinsuke Sakai , Tatsuya Kawahara

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-04 Mingkun Huang , Meng Cai , Jun Zhang , Yang Zhang , Yongbin You , Yi He , Zejun Ma

We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output. We show that the imitation learning algorithms designed to…

Computation and Language · Computer Science 2022-03-18 Sweta Agrawal , Marine Carpuat

Although attention based end-to-end models have achieved promising performance in speech recognition, the multi-pass forward computation in beam-search increases inference time cost, which limits their practical applications. To address…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-07 Ye Bai , Jiangyan Yi , Jianhua Tao , Zhengkun Tian , Zhengqi Wen , Shuai Zhang

Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predictions. We propose a parallel decoding sequence-to-sequence…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Kunyu Shi , Qi Dong , Luis Goncalves , Zhuowen Tu , Stefano Soatto

Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…

Computation and Language · Computer Science 2023-10-20 Yi Bin , Wenhao Shi , Bin Ji , Jipeng Zhang , Yujuan Ding , Yang Yang

Language is by its very nature incremental in how it is produced and processed. This property can be exploited by NLP systems to produce fast responses, which has been shown to be beneficial for real-time interactive applications. Recent…

Computation and Language · Computer Science 2023-05-19 Patrick Kahardipraja , Brielen Madureira , David Schlangen

We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Somshubra Majumdar , Jagadeesh Balam , Oleksii Hrinchuk , Vitaly Lavrukhin , Vahid Noroozi , Boris Ginsburg

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Machine Learning · Computer Science 2023-10-06 Leonardo Emili , Thiago Fraga-Silva , Ernest Pusateri , Markus Nußbaum-Thom , Youssef Oualil