English
Related papers

Related papers: Multi-Modal Data Augmentation for End-to-End ASR

200 papers

We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-26 Florian Lux , Ngoc Thang Vu

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

To let the state-of-the-art end-to-end ASR model enjoy data efficiency, as well as much more unpaired text data by multi-modal training, one needs to address two problems: 1) the synchronicity of feature sampling rates between speech and…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Yuhang Yang , Haihua Xu , Hao Huang , Eng Siong Chng , Sheng Li

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

Sound · Computer Science 2024-06-17 Naijun Zheng , Xucheng Wan , Kai Liu , Ziqing Du , Zhou Huan

In this paper, we propose a language-universal adapter learning framework based on a pre-trained model for end-to-end multilingual automatic speech recognition (ASR). For acoustic modeling, the wav2vec 2.0 pre-trained model is fine-tuned by…

Computation and Language · Computer Science 2023-03-03 Zhijie Shen , Wu Guo , Bin Gu

A simplified speech recognition system that uses the maximum mutual information (MMI) criterion is considered. End-to-end training using gradient descent is suggested, similarly to the training of connectionist temporal classification…

Machine Learning · Computer Science 2017-07-18 Lior Fritz , David Burshtein

Combining large language models with logical reasoning enhances their capacity to address problems in a robust and reliable manner. Nevertheless, the intricate nature of logical reasoning poses challenges when gathering reliable data from…

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-07 Rohit Prabhavalkar , Takaaki Hori , Tara N. Sainath , Ralf Schlüter , Shinji Watanabe

Due to the rising awareness of privacy protection and the voluminous scale of speech data, it is becoming infeasible for Automatic Speech Recognition (ASR) system developers to train the acoustic model with complete data as before. For…

Sound · Computer Science 2024-10-22 Victor Junqiu Wei , Weicheng Wang , Di Jiang , Conghui Tan , Rongzhong Lian

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Sound · Computer Science 2024-02-07 Zhenyu Zhou , Junhui Chen , Namin Wang , Lantian Li , Dong Wang

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-02 Yosuke Higuchi , Tetsuji Ogawa , Tetsunori Kobayashi , Shinji Watanabe

Advances in machine learning have made it possible to perform various text and speech processing tasks, such as automatic speech recognition (ASR), in an end-to-end (E2E) manner. E2E approaches utilizing pre-trained models are gaining…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-07 Yukiya Hono , Koh Mitsuda , Tianyu Zhao , Kentaro Mitsui , Toshiaki Wakatsuki , Kei Sawada

Mispronunciation detection and diagnosis (MDD) is a core component of computer-assisted pronunciation training (CAPT). Most of the existing MDD approaches focus on dealing with categorical errors (viz. one canonical phone is substituted by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-31 Bi-Cheng Yan , Meng-Che Wu , Hsiao-Tsung Hung , Berlin Chen

We propose a novel approach to optimizing a byte-level representation for end-to-end automatic speech recognition (ASR). Byte-level representation is often used by large scale multilingual ASR systems when the character set of the supported…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-06 Roger Hsiao , Liuhui Deng , Erik McDermott , Ruchir Travadi , Xiaodan Zhuang

In the area of multi-domain speech recognition, research in the past focused on hybrid acoustic models to build cross-domain and domain-invariant speech recognition systems. In this paper, we empirically examine the difference in behavior…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-10 Thai-Son Nguyen , Sebastian Stüker , Alex Waibel

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Computation and Language · Computer Science 2026-02-17 Ligong Lei , Wenwen Lu , Xudong Pang , Zaokere Kadeer , Aishan Wumaier

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

Sound · Computer Science 2020-11-10 Ashutosh Pandey , Chunxi Liu , Yun Wang , Yatharth Saraf

Sequence-to-Sequence (S2S) models recently started to show state-of-the-art performance for automatic speech recognition (ASR). With these large and deep models overfitting remains the largest problem, outweighing performance improvements…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-04 Thai-Son Nguyen , Sebastian Stueker , Jan Niehues , Alex Waibel

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

Computation and Language · Computer Science 2023-03-03 Philipp Klumpp , Pooja Chitkara , Leda Sarı , Prashant Serai , Jilong Wu , Irina-Elena Veliche , Rongqing Huang , Qing He

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-22 Yufeng Yang , Ashutosh Pandey , DeLiang Wang