1 code implementation • 28 Jan 2024 • Desh Raj, Matthew Wiesner, Matthew Maciejewski, Leibny Paola Garcia-Perera, Daniel Povey, Sanjeev Khudanpur
The Streaming Unmixing and Recognition Transducer (SURT) has recently become a popular framework for continuous, streaming, multi-talker speech recognition (ASR).
1 code implementation • 17 Oct 2023 • Zengwei Yao, Liyong Guo, Xiaoyu Yang, Wei Kang, Fangjun Kuang, Yifan Yang, Zengrui Jin, Long Lin, Daniel Povey
The Conformer has become the most popular encoder model for automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 26 Sep 2023 • Dongji Gao, Hainan Xu, Desh Raj, Leibny Paola Garcia Perera, Daniel Povey, Sanjeev Khudanpur
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 15 Sep 2023 • Wei Kang, Xiaoyu Yang, Zengwei Yao, Fangjun Kuang, Yifan Yang, Liyong Guo, Long Lin, Daniel Povey
In this paper, we introduce Libriheavy, a large-scale ASR corpus consisting of 50, 000 hours of read English speech derived from LibriVox.
1 code implementation • 14 Sep 2023 • Yifan Yang, Feiyu Shen, Chenpeng Du, Ziyang Ma, Kai Yu, Daniel Povey, Xie Chen
Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ natural language processing techniques.
2 code implementations • 14 Sep 2023 • Xiaoyu Yang, Wei Kang, Zengwei Yao, Yifan Yang, Liyong Guo, Fangjun Kuang, Long Lin, Daniel Povey
An additional style prompt can be given to the text encoder and guide the ASR system to output different styles of transcriptions.
no code implementations • 12 Aug 2023 • Han Zhu, Dongji Gao, Gaofeng Cheng, Daniel Povey, Pengyuan Zhang, Yonghong Yan
Firstly, a generalized CTC loss function is introduced to handle noisy pseudo-labels by accepting alternative tokens in the positions of incorrect tokens.
1 code implementation • 18 Jun 2023 • Desh Raj, Daniel Povey, Sanjeev Khudanpur
The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR).
no code implementations • 1 Jun 2023 • Dongji Gao, Matthew Wiesner, Hainan Xu, Leibny Paola Garcia, Daniel Povey, Sanjeev Khudanpur
Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the performance of ASR models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 19 May 2023 • Zengwei Yao, Wei Kang, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Yifan Yang, Long Lin, Daniel Povey
Our work is open-sourced and publicly available https://github. com/k2-fsa/k2.
1 code implementation • 19 May 2023 • Yifan Yang, Xiaoyu Yang, Liyong Guo, Zengwei Yao, Wei Kang, Fangjun Kuang, Long Lin, Xie Chen, Daniel Povey
Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems.
2 code implementations • 10 Dec 2022 • Desh Raj, Daniel Povey, Sanjeev Khudanpur
In this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-based pipelines, including batched processing of frequencies and segments, to provide 300x speed-up over CPU-based inference.
Ranked #2 on Speech Recognition on LibriCSS
1 code implementation • 31 Oct 2022 • Wei Kang, Liyong Guo, Fangjun Kuang, Long Lin, Mingshuang Luo, Zengwei Yao, Xiaoyu Yang, Piotr Żelasko, Daniel Povey
In this work, we introduce a constrained version of transducer loss to learn strictly monotonic alignments between the sequences; we also improve the standard greedy search and beam search algorithms by limiting the number of symbols that can be emitted per time step in transducer decoding, making it more efficient to decode in parallel with batches.
1 code implementation • 31 Oct 2022 • Liyong Guo, Xiaoyu Yang, Quandong Wang, Yuxiang Kong, Zengwei Yao, Fan Cui, Fangjun Kuang, Wei Kang, Long Lin, Mingshuang Luo, Piotr Zelasko, Daniel Povey
Although on-the-fly teacher label generation tackles this issue, the training speed is significantly slower as the teacher model has to be evaluated every batch.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 31 Oct 2022 • Wei Kang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Long Lin, Piotr Żelasko, Daniel Povey
In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 23 Jun 2022 • Fangjun Kuang, Liyong Guo, Wei Kang, Long Lin, Mingshuang Luo, Zengwei Yao, Daniel Povey
The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with naturally streaming recognition.
2 code implementations • 13 Jun 2021 • Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10, 000 hours of high quality labeled audio suitable for supervised training, and 40, 000 hours of total audio suitable for semi-supervised and unsupervised training.
Ranked #1 on Speech Recognition on GigaSpeech
2 code implementations • 3 Apr 2021 • Junbo Zhang, Zhiwen Zhang, Yongqing Wang, Zhiyong Yan, Qiong Song, YuKai Huang, Ke Li, Daniel Povey, Yujun Wang
This paper introduces a new open-source speech corpus named "speechocean762" designed for pronunciation assessment use, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children.
Ranked #7 on Phone-level pronunciation scoring on speechocean762
1 code implementation • 8 Mar 2021 • Ke Li, Daniel Povey, Sanjeev Khudanpur
This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 8 Feb 2021 • Yiming Wang, Hang Lv, Daniel Povey, Lei Xie, Sanjeev Khudanpur
Modern wake word detection systems usually rely on neural networks for acoustic modeling.
1 code implementation • 3 Nov 2020 • Desh Raj, Leibny Paola Garcia-Perera, Zili Huang, Shinji Watanabe, Daniel Povey, Andreas Stolcke, Sanjeev Khudanpur
Several advances have been made recently towards handling overlapping speech for speaker diarization.
Audio and Speech Processing Sound
1 code implementation • 20 May 2020 • Yiwen Shao, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
We present PyChain, a fully parallelized PyTorch implementation of end-to-end lattice-free maximum mutual information (LF-MMI) training for the so-called \emph{chain models} in the Kaldi automatic speech recognition (ASR) toolkit.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 17 May 2020 • Yiming Wang, Hang Lv, Daniel Povey, Lei Xie, Sanjeev Khudanpur
Always-on spoken language interfaces, e. g. personal digital assistants, rely on a wake word to start processing spoken input.
no code implementations • 20 Apr 2020 • Shinji Watanabe, Michael Mandel, Jon Barker, Emmanuel Vincent, Ashish Arora, Xuankai Chang, Sanjeev Khudanpur, Vimal Manohar, Daniel Povey, Desh Raj, David Snyder, Aswin Shanmugam Subramanian, Jan Trmal, Bar Ben Yair, Christoph Boeddeker, Zhaoheng Ni, Yusuke Fujita, Shota Horiguchi, Naoyuki Kanda, Takuya Yoshioka, Neville Ryant
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6).
1 code implementation • 14 Feb 2020 • Zili Huang, Shinji Watanabe, Yusuke Fujita, Paola Garcia, Yiwen Shao, Daniel Povey, Sanjeev Khudanpur
Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem.
1 code implementation • 22 Oct 2019 • Hugo Braun, Justin Luitjens, Ryan Leary, Tim Kaldewey, Daniel Povey
We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs).
no code implementations • 13 Sep 2019 • Desh Raj, David Snyder, Daniel Povey, Sanjeev Khudanpur
Deep neural network based speaker embeddings, such as x-vectors, have been shown to perform well in text-independent speaker recognition/verification tasks.
no code implementations • Interspeech 2018 2018 • Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur
We present our work on end-to-end training of acoustic models using the lattice-free maximum mutual information (LF-MMI) objective function in the context of hidden Markov models.
Ranked #1 on Speech Recognition on Switchboard (300hr)
1 code implementation • Interspeech 2018 2018 • Daniel Povey, Gaofeng Cheng, Yiming Wang, Ke Li, Hainan Xu, Mahsa Yarmohammadi, Sanjeev Khudanpur
Time Delay Neural Networks (TDNNs), also known as onedimensional Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural network architecture for speech recognition.
no code implementations • ICASSP 2018 • Hainan Xu, Ke Li, Yiming Wang, Jian Wang, Shiyin Kang, Xie Chen, Daniel Povey, Sanjeev Khudanpur
In this paper we describe an extension of the Kaldi software toolkit to support neural-based language modeling, intended for use in automatic speech recognition (ASR) and related tasks.
Ranked #36 on Speech Recognition on LibriSpeech test-other (using extra training data)
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 9 Apr 2018 • Zhehuai Chen, Justin Luitjens, Hainan Xu, Yiming Wang, Daniel Povey, Sanjeev Khudanpur
We describe initial work on an extension of the Kaldi toolkit that supports weighted finite-state transducer (WFST) decoding on Graphics Processing Units (GPUs).
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 • INTERSPEECH 2016 2016 • Daniel Povey, Vijayaditya Peddinti, Daniel Galvez, Pegah Ghahrmani, Vimal Manohar, Xingyu Na, Yiming Wang, Sanjeev Khudanpur
Models trained with LFMMI provide a relative word error rate reduction of ∼11. 5%, over those trained with cross-entropy objective function, and ∼8%, over those trained with cross-entropy and sMBR objective functions.
Ranked #4 on Speech Recognition on WSJ eval92
2 code implementations • 28 Oct 2015 • David Snyder, Guoguo Chen, Daniel Povey
This report introduces a new corpus of music, speech, and noise.
Sound
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.