English
Related papers

Related papers: UniEnc-CASSNAT: An Encoder-only Non-autoregressive…

200 papers

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have…

Sound · Computer Science 2019-05-16 Yi Luo , Nima Mesgarani

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…

Computation and Language · Computer Science 2017-01-11 Ying Zhang , Mohammad Pezeshki , Philemon Brakel , Saizheng Zhang , Cesar Laurent Yoshua Bengio , Aaron Courville

Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while maintaining low latency often leads to a tendency for…

Computation and Language · Computer Science 2023-10-24 Zhengrui Ma , Shaolei Zhang , Shoutao Guo , Chenze Shao , Min Zhang , Yang Feng

Unified Speech Recognition (USR) has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition, achieving state-of-the-art results on in-distribution benchmarks. However, its…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Alexandros Haliassos , Rodrigo Mira , Stavros Petridis

Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature. To this end, non-autoregressive (NAR) approaches…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-13 Tianzi Wang , Xurong Xie , Zengrui Jin , Mengzhe Geng , Jiajun Deng , Zhaoqing Li , Shoukang Hu , Shujie Hu , Guinan Li , Mingyu Cui , Helen Meng , Xunying Liu

The two most popular loss functions for streaming end-to-end automatic speech recognition (ASR) are RNN-Transducer (RNN-T) and connectionist temporal classification (CTC). Between these two loss types we can classify the monotonic RNN-T…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-25 Niko Moritz , Frank Seide , Duc Le , Jay Mahadeokar , Christian Fuegen

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-18 Hexin Liu , Haoyang Zhang , Qiquan Zhang , Xiangyu Zhang , Dongyuan Shi , Eng Siong Chng , Haizhou Li

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.…

Computation and Language · Computer Science 2019-06-25 Chenze Shao , Yang Feng , Jinchao Zhang , Fandong Meng , Xilin Chen , Jie Zhou

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-10 Hongfei Xue , Qijie Shao , Peikun Chen , Pengcheng Guo , Lei Xie , Jie Liu

The kNN-CTC model has proven to be effective for monolingual automatic speech recognition (ASR). However, its direct application to multilingual scenarios like code-switching, presents challenges. Although there is potential for performance…

Computation and Language · Computer Science 2025-01-20 Jiaming Zhou , Shiwan Zhao , Hui Wang , Tian-Hao Zhang , Haoqin Sun , Xuechen Wang , Yong Qin

This paper proposes CTC-based non-autoregressive ASR with self-conditioned folded encoders. The proposed method realizes non-autoregressive ASR with fewer parameters by folding the conventional stack of encoders into only two blocks; base…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-18 Tatsuya Komatsu

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Takafumi Moriya , Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Takahiro Shinozaki

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short…

Sound · Computer Science 2018-04-19 Yi Luo , Nima Mesgarani

While Separate Source-Channel Coding (SSCC) retains the practical benefits of modular system design, its effectiveness in noisy text transmission is fundamentally constrained by the fragility of autoregressive source decoding. In low-SNR…

Information Theory · Computer Science 2026-05-08 Ziqiong Wang , Rongpeng Li

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Computation and Language · Computer Science 2020-11-20 Jay Mahadeokar , Yuan Shangguan , Duc Le , Gil Keren , Hang Su , Thong Le , Ching-Feng Yeh , Christian Fuegen , Michael L. Seltzer

Multi-talker speech recognition (MTASR) faces unique challenges in disentangling and transcribing overlapping speech. To address these challenges, this paper investigates the role of Connectionist Temporal Classification (CTC) in speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-06 Jiawen Kang , Lingwei Meng , Mingyu Cui , Yuejiao Wang , Xixin Wu , Xunying Liu , Helen Meng

Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR). T-SOT effectively handles overlapped speech by representing multi-talker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-18 Jian Wu , Naoyuki Kanda , Takuya Yoshioka , Rui Zhao , Zhuo Chen , Jinyu Li

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…

Computation and Language · Computer Science 2021-02-19 Harsh Shrivastava , Ankush Garg , Yuan Cao , Yu Zhang , Tara Sainath

We propose a cross-modal transformer-based neural correction models that refines the output of an automatic speech recognition (ASR) system so as to exclude ASR errors. Generally, neural correction models are composed of encoder-decoder…

Computation and Language · Computer Science 2021-07-06 Tomohiro Tanaka , Ryo Masumura , Mana Ihori , Akihiko Takashima , Takafumi Moriya , Takanori Ashihara , Shota Orihashi , Naoki Makishima