English
Related papers

Related papers: Bypass Temporal Classification: Weakly Supervised …

200 papers

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to disfluency, filter words, and other errata…

Computation and Language · Computer Science 2021-02-23 Junwei Liao , Yu Shi , Ming Gong , Linjun Shou , Sefik Eskimez , Liyang Lu , Hong Qu , Michael Zeng

End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many applications, especially for subtitling and computer-aided…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-14 Xianzhao Chen , Yist Y. Lin , Kang Wang , Yi He , Zejun Ma

Modern deep learning models often achieve high overall performance, but consistently fail on specific subgroups. Group distributionally robust optimization (group DRO) addresses this problem by minimizing the worst-group loss, but it fails…

Text to speech (TTS) and automatic speech recognition (ASR) are two dual tasks in speech processing and both achieve impressive performance thanks to the recent advance in deep learning and large amount of aligned speech and text data.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Yi Ren , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , Tie-Yan Liu

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-21 Murali Karthick Baskar , Shinji Watanabe , Ramon Astudillo , Takaaki Hori , Lukáš Burget , Jan Černocký

Recently, data-driven based Automatic Speech Recognition (ASR) systems have achieved state-of-the-art results. And transfer learning is often used when those existing systems are adapted to the target domain, e.g., fine-tuning, retraining.…

Sound · Computer Science 2019-04-18 Jiabin Xue , Jiqing Han , Tieran Zheng , Xiang Gao , Jiaxing Guo

Previous work has shown that neural encoder-decoder speech recognition can be improved with hierarchical multitask learning, where auxiliary tasks are added at intermediate layers of a deep encoder. We explore the effect of hierarchical…

Computation and Language · Computer Science 2019-03-08 Kalpesh Krishna , Shubham Toshniwal , Karen Livescu

Alzheimer's disease (AD) is a progressive neurodegenerative disease and recently attracts extensive attention worldwide. Speech technology is considered a promising solution for the early diagnosis of AD and has been enthusiastically…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-05 Ying Qin , Wei Liu , Zhiyuan Peng , Si-Ioi Ng , Jingyu Li , Haibo Hu , Tan Lee

Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-11 Jing Du , Shiliang Pu , Qinbo Dong , Chao Jin , Xin Qi , Dian Gu , Ru Wu , Hongwei Zhou

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Computation and Language · Computer Science 2019-10-29 Qiao Cheng , Meiyuan Fang , Yaqian Han , Jin Huang , Yitao Duan

Many machine learning problems such as speech recognition, gesture recognition, and handwriting recognition are concerned with simultaneous segmentation and labeling of sequence data. Latent-dynamic conditional random field (LDCRF) is a…

Machine Learning · Computer Science 2016-09-07 Amir Ahooye Atashin , Kamaledin Ghiasi-Shirazi , Ahad Harati

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently,…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-10 Morgane Rivière , Armand Joulin , Pierre-Emmanuel Mazaré , Emmanuel Dupoux

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

Computation and Language · Computer Science 2019-01-15 Ramon Sanabria , Florian Metze

\textbf{Objectives}: We aimed to investigate how errors from automatic speech recognition (ASR) systems affect dementia classification accuracy, specifically in the ``Cookie Theft'' picture description task. We aimed to assess whether…

Computation and Language · Computer Science 2024-01-12 Changye Li , Weizhe Xu , Trevor Cohen , Serguei Pakhomov

Topic classification systems on spoken documents usually consist of two modules: an automatic speech recognition (ASR) module to convert speech into text and a text topic classification (TTC) module to predict the topic class from the…

Computation and Language · Computer Science 2021-06-17 Tan Liu , Wu Guo , Bin Gu

Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed for broad deployment, they pose challenges for specialist…

Automatic Speech Recognition (ASR) is an imperfect process that results in certain mismatches in ASR output text when compared to plain written text or transcriptions. When plain text data is to be used to train systems for spoken language…

Computation and Language · Computer Science 2021-04-02 Prashant Serai , Vishal Sunder , Eric Fosler-Lussier

The speech chain mechanism integrates automatic speech recognition (ASR) and text-to-speech synthesis (TTS) modules into a single cycle during training. In our previous work, we applied a speech chain mechanism as a semi-supervised…

Computation and Language · Computer Science 2018-11-01 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstrated superiority in solving the RTC problem. However, the…

Machine Learning · Computer Science 2023-02-16 Zhenhao Huang , Yuning Qiu , Xinqi Chen , Weijun Sun , Guoxu Zhou

This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-27 Aleksandr Laptev , Somshubra Majumdar , Boris Ginsburg
‹ Prev 1 4 5 6 7 8 10 Next ›