Results 51 to 60 of about 47,965 (148)

Multilingual Speech Recognition with a Single End-to-End Model [PDF]

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models are well suited for multilingual ASR because they encapsulate an acoustic, pronunciation and language model ...
Shubham Toshniwal, Tara N. Sainath, Ron J. Weiss, Bo Li 0028, Pedro J. Moreno 0001, Eugene Weinstein, Kanishka Rao   +6 more
openaire   +2 more sources

Acoustic Model Fusion For End-to-End Speech Recognition

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2023
Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the acoustic model (AM) and the language model (LM), in a single network trained on audio-text pairs. Despite this simpler
Zhihong Lei, Mingbin Xu, Shiyi Han, Leo Liu, Zhen Huang 0001, Tim Ng, Yuanyuan Zhang, Ernest Pusateri, Mirko Hannemann, Yaqiao Deng, Man-Hung Siu   +10 more
openaire   +2 more sources

A Light-Weight Autoregressive CNN-Based Frame Level Transducer Decoder for End-to-End ASR

Applied Sciences
A convolutional neural network (CNN) transducer decoder was proposed to reduce the decoding time of an end-to-end automatic speech recognition (ASR) system while maintaining accuracy.
Hyeon-Kyu Noh, Hong-June Park
doaj   +1 more source

Attention-based latent features for jointly trained end-to-end automatic speech recognition with modified speech enhancement

Journal of King Saud University: Computer and Information Sciences, 2023
In this paper, we propose a joint training framework that efficiently combines time-domain speech enhancement (SE) with an end-to-end (E2E) automatic speech recognition (ASR) system utilizing attention-based latent features.
Da-Hee Yang, Joon-Hyuk Chang
doaj   +1 more source

Dialog-Context Aware end-to-end Speech Recognition [PDF]

2018 IEEE Spoken Language Technology Workshop (SLT), 2018
Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The recent progress in end-to-end speech recognition systems promises to integrate all available information (e.g ...
Suyoun Kim, Florian Metze
openaire   +2 more sources

End-to-End Speech Recognition: A Survey

IEEE/ACM Transactions on Audio, Speech, and Language Processing
Submitted to IEEE/ACM Transactions on Audio, Speech, and Language ...
Rohit Prabhavalkar, Takaaki Hori, Tara N. Sainath, Ralf Schlüter, Shinji Watanabe 0001   +4 more
openaire   +3 more sources

Improving End-to-End Models for Children’s Speech Recognition

Applied Sciences
Children’s Speech Recognition (CSR) is a challenging task due to the high variability in children’s speech patterns and limited amount of available annotated children’s speech data. We aim to improve CSR in the often-occurring scenario that no children’s
Tanvina Patel, Odette Scharenborg
doaj   +1 more source

End-to-end Music-mixed Speech Recognition

, 2020
Automatic speech recognition (ASR) in multimedia content is one of the promising applications, but speech data in this kind of content are frequently mixed with background music, which is harmful for the performance of ASR. In this study, we propose a method for improving ASR with background music based on time-domain source separation. We utilize Conv-
Jeongwoo Woo, Masato Mimura, Kazuyoshi Yoshii, Tatsuya Kawahara   +3 more
openaire   +3 more sources

Comparative Study on End-to-End Speech Recognition Using Pre-trained Models [PDF]

Fayoum University Journal of Engineering
In the field of speech and audio signal processing, pre-trained models (PTMs) are commonly available. Pre-trained models (PTMs) offer a collection of initial weights and biases that may be adjusted for a particular task, which makes them a popular ...
Martha Ghobrial, Amr Gody, Sayed Muhammad   +2 more
doaj   +1 more source

Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks

Applied Sciences, 2021
The performance of automatic speech recognition (ASR) may be degraded when accented speech is recognized because the speech has some linguistic differences from standard speech.
Hyeong-Ju Na, Jeong-Sik Park
doaj   +1 more source