1 code implementation • 27 Oct 2014 • Daniel Povey, Xiaohui Zhang, Sanjeev Khudanpur
However, we have another method, an approximate and efficient implementation of Natural Gradient for Stochastic Gradient Descent (NG-SGD), which seems to allow our periodic-averaging method to work well, as well as substantially improving the convergence of SGD on a single machine.
no code implementations • 12 Jun 2017 • Xiaohui Zhang, Vimal Manohar, Daniel Povey, Sanjeev Khudanpur
Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations.
no code implementations • 17 Apr 2018 • Yingjun Ye, Xiaohui Zhang, Jian Sun
Therefore, a framework of the decision-making training and learning is put forward in this paper.
no code implementations • LREC 2020 • Chunxi Liu, Qiaochu Zhang, Xiaohui Zhang, Kritika Singh, Yatharth Saraf, Geoffrey Zweig
Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations.
no code implementations • 2 Oct 2019 • Duc Le, Xiaohui Zhang, Weiyi Zheng, Christian Fügen, Geoffrey Zweig, Michael L. Seltzer
There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor grapheme-phoneme correspondence.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 22 Oct 2019 • Yongqiang Wang, Abdel-rahman Mohamed, Duc Le, Chunxi Liu, Alex Xiao, Jay Mahadeokar, Hongzhao Huang, Andros Tjandra, Xiaohui Zhang, Frank Zhang, Christian Fuegen, Geoffrey Zweig, Michael L. Seltzer
We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition.
Ranked #23 on Speech Recognition on LibriSpeech test-other (using extra training data)
1 code implementation • 23 Oct 2019 • Andros Tjandra, Chunxi Liu, Frank Zhang, Xiaohui Zhang, Yongqiang Wang, Gabriel Synnaeve, Satoshi Nakamura, Geoffrey Zweig
As our motivation is to allow acoustic models to re-examine their input features in light of partial hypotheses we introduce intermediate model heads and loss function.
no code implementations • 19 May 2020 • Frank Zhang, Yongqiang Wang, Xiaohui Zhang, Chunxi Liu, Yatharth Saraf, Geoffrey Zweig
In this work, we first show that on the widely used LibriSpeech benchmark, our transformer-based context-dependent connectionist temporal classification (CTC) system produces state-of-the-art results.
Ranked #17 on Speech Recognition on LibriSpeech test-other (using extra training data)
no code implementations • 9 Nov 2020 • Xiaohui Zhang, Frank Zhang, Chunxi Liu, Kjell Schubert, Julian Chan, Pradyot Prakash, Jun Liu, Ching-Feng Yeh, Fuchun Peng, Yatharth Saraf, Geoffrey Zweig
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on three popular training criteria: LF-MMI, CTC and RNN-T.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 6 Jul 2021 • Xiaohui Zhang, Varun A. Kelkar, Jason Granstedt, Hua Li, Mark A. Anastasio
The presented study highlights the urgent need for the objective assessment of DL-SR methods and suggests avenues for improving their efficacy in medical imaging applications.
no code implementations • 9 Jul 2021 • Xiaohui Zhang, Vimal Manohar, David Zhang, Frank Zhang, Yangyang Shi, Nayan Singhal, Julian Chan, Fuchun Peng, Yatharth Saraf, Mike Seltzer
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 7 Oct 2021 • Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer
This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution.
no code implementations • 7 Oct 2021 • Jialu Li, Vimal Manohar, Pooja Chitkara, Andros Tjandra, Michael Picheny, Frank Zhang, Xiaohui Zhang, Yatharth Saraf
Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 15 Oct 2021 • Haichuan Yang, Yuan Shangguan, Dilin Wang, Meng Li, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra
From wearables to powerful smart devices, modern automatic speech recognition (ASR) models run on a variety of edge devices with different computational budgets.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 18 Nov 2021 • Chunxi Liu, Michael Picheny, Leda Sari, Pooja Chitkara, Alex Xiao, Xiaohui Zhang, Mark Chou, Andres Alvarado, Caner Hazirbas, Yatharth Saraf
This paper presents initial Speech Recognition results on "Casual Conversations" -- a publicly released 846 hour corpus designed to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of metadata, including age, gender, and skin tone.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 23 Jun 2022 • Zong Fan, Xiaohui Zhang, Jacob A. Gasienica, Jennifer Potts, Su Ruan, Wade Thorstad, Hiram Gay, Pengfei Song, Xiaowei Wang, Hua Li
Deep learning (DL) techniques have been extensively utilized for medical image classification.
no code implementations • 11 Oct 2022 • Zong Fan, Ping Gong, Shanshan Tang, Christine U. Lee, Xiaohui Zhang, Pengfei Song, Shigao Chen, Hua Li
By use of the attention mechanism, the auxiliary lesion-aware network can optimize multi-scale intermediate feature maps and extract rich semantic information to improve classification and localization performance.
no code implementations • 20 Oct 2022 • Desh Raj, Junteng Jia, Jay Mahadeokar, Chunyang Wu, Niko Moritz, Xiaohui Zhang, Ozlem Kalinli
In this paper, we investigate anchored speech recognition to make neural transducers robust to background speech.
no code implementations • 4 Apr 2023 • Anurag Kumar, Ke Tan, Zhaoheng Ni, Pranay Manocha, Xiaohui Zhang, Ethan Henderson, Buye Xu
To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed.
1 code implementation • 10 Apr 2023 • Brian Yan, Jiatong Shi, Yun Tang, Hirofumi Inaguma, Yifan Peng, Siddharth Dalmia, Peter Polák, Patrick Fernandes, Dan Berrebbi, Tomoki Hayashi, Xiaohui Zhang, Zhaoheng Ni, Moto Hira, Soumi Maiti, Juan Pino, Shinji Watanabe
ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community.
3 code implementations • arXiv 2023 • Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli
Expanding the language coverage of speech technology has the potential to improve access to information for many more people.
no code implementations • 8 Jun 2023 • Xiaohui Zhang, Jiangyan Yi, JianHua Tao, Chenlong Wang, Le Xu, Ruibo Fu
During the inference stage, these adaptation matrices are combined with the existing model to generate the final prediction output.
no code implementations • 9 Jun 2023 • Chenglong Wang, Jiangyan Yi, Xiaohui Zhang, JianHua Tao, Le Xu, Ruibo Fu
Self-supervised speech models are a rapidly developing research topic in fake audio detection.
1 code implementation • 7 Aug 2023 • Xiaohui Zhang, Jiangyan Yi, JianHua Tao, Chenglong Wang, Chuyuan Zhang
The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets.
no code implementations • 19 Sep 2023 • Zhaoheng Ni, Sravya Popuri, Ning Dong, Kohei Saijo, Xiaohui Zhang, Gael Le Lan, Yangyang Shi, Vikas Chandra, Changhan Wang
High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 3 Oct 2023 • Xiaohui Zhang, Mimi Tan, Mansour Nabil, Richa Shukla, Shaleen Vasavada, Sharmila Anandasabapathy, Mark A. Anastasio, Elena Petrova
Aim: To improve the efficiency of endoscopic screening, we proposed a novel end-expandable endoscopic optical fiber probe for larger field of visualization and employed a deep learning-based image super-resolution (DL-SR) method to overcome the issue of limited sampling capability.
1 code implementation • 27 Oct 2023 • Jeff Hwang, Moto Hira, Caroline Chen, Xiaohui Zhang, Zhaoheng Ni, Guangzhi Sun, Pingchuan Ma, Ruizhe Huang, Vineel Pratap, Yuekai Zhang, Anurag Kumar, Chin-Yun Yu, Chuang Zhu, Chunxi Liu, Jacob Kahn, Mirco Ravanelli, Peng Sun, Shinji Watanabe, Yangyang Shi, Yumeng Tao, Robin Scheibler, Samuele Cornell, Sean Kim, Stavros Petridis
TorchAudio is an open-source audio and speech processing library built for PyTorch.
1 code implementation • 17 Nov 2023 • Xiaohui Zhang, Jaehong Yoon, Mohit Bansal, Huaxiu Yao
This optimization process is controlled by a gradient modification mechanism to prevent the shared head from losing previously acquired information.
1 code implementation • 15 Dec 2023 • Xiaohui Zhang, Jiangyan Yi, Chenglong Wang, Chuyuan Zhang, Siding Zeng, JianHua Tao
The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms.
1 code implementation • 16 Jan 2024 • Xiaohui Zhang, Eric C. Landsness, Hanyang Miao, Wei Chen, Michelle Tang, Lindsey M. Brier, Joseph P. Culver, Jin-Moo Lee, Mark A. Anastasio
Comparison with Existing Method: On a 3-hour WFCI recording, the CNN-BiLSTM achieved a kappa of 0. 67, comparable to a kappa of 0. 65 corresponding to the human EEG/EMG-based scoring.
no code implementations • 6 Feb 2024 • Songnan Yang, Xiaohui Zhang, Shiliang Zhang, Xuehui Ma, Wenqi Bai, Yushuai Li, TingWen Huang
We integrate the developed mechanism with the TA-LSTM, and calibrate the predicted heading angles to gain resistance against geomagnetic anomalies.