Zipformer: A faster and better encoder for automatic speech recognition

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

Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context

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.

PromptASR for contextualized ASR with controllable style

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.

Automatic Speech Recognition speech-recognition +1

Blank-regularized CTC for Frame Skipping in Neural Transducer

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.

Automatic Speech Recognition speech-recognition +1

Delay-penalized CTC implemented based on Finite State Transducer

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.

Attribute

Exploring Representation Learning for Small-Footprint Keyword Spotting

no code implementations • 20 Mar 2023 • Fan Cui, Liyong Guo, Quandong Wang, Peng Gao, Yujun Wang

To address those challenges, we explore representation learning for KWS by self-supervised contrastive learning and self-training with pretrained model.

Contrastive Learning Representation Learning +1

Relate auditory speech to EEG by shallow-deep attention-based network

no code implementations • 20 Mar 2023 • Fan Cui, Liyong Guo, Lang He, Jiyao Liu, Ercheng Pei, Yujun Wang, Dongmei Jiang

Electroencephalography (EEG) plays a vital role in detecting how brain responses to different stimulus.

Data Augmentation Deep Attention +1

Delay-penalized transducer for low-latency streaming ASR

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

Fast and parallel decoding for transducer

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.

speech-recognition Speech Recognition

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

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

Pruned RNN-T for fast, memory-efficient ASR training

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.

speech-recognition Speech Recognition

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

5 code implementations • 10 Dec 2020 • BinBin Zhang, Di wu, Zhuoyuan Yao, Xiong Wang, Fan Yu, Chao Yang, Liyong Guo, Yaguang Hu, Lei Xie, Xin Lei

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.

Sentence speech-recognition +1