English
Related papers

Related papers: Exploring Pre-training with Alignments for RNN Tra…

200 papers

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

Computation and Language · Computer Science 2016-06-29 Kyuyeon Hwang , Wonyong Sung

This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of…

Audio and Speech Processing · Electrical Eng. & Systems 2019-11-13 Takaki Makino , Hank Liao , Yannis Assael , Brendan Shillingford , Basilio Garcia , Otavio Braga , Olivier Siohan

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Semin Kim , Joun Yeop Lee , Nam Soo Kim

We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. This hybrid approach maintains RNN-T's streaming capability…

Machine Learning · Computer Science 2026-03-02 Hainan Xu , Vladimir Bataev , Travis M. Bartley , Jagadeesh Balam

This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-09 Aleksandr Laptev , Boris Ginsburg

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-12 Jian Luo , Jianzong Wang , Ning Cheng , Jing Xiao

Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…

Sound · Computer Science 2020-11-19 Kun Wei , Pengcheng Guo , Hang Lv , Zhen Tu , Lei Xie

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Wei Han , Zhengdong Zhang , Yu Zhang , Jiahui Yu , Chung-Cheng Chiu , James Qin , Anmol Gulati , Ruoming Pang , Yonghui Wu

This paper advances the design of CTC-based all-neural (or end-to-end) speech recognizers. We propose a novel symbol inventory, and a novel iterated-CTC method in which a second system is used to transform a noisy initial output into a…

Computation and Language · Computer Science 2022-02-24 G. Zweig , C. Yu , J. Droppo , A. Stolcke

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

Computation and Language · Computer Science 2016-06-21 Liang Lu , Lingpeng Kong , Chris Dyer , Noah A. Smith , Steve Renals

In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract…

Computer Vision and Pattern Recognition · Computer Science 2021-02-15 Pingchuan Ma , Stavros Petridis , Maja Pantic

RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-30 Dario Albesano , Jesús Andrés-Ferrer , Nicola Ferri , Puming Zhan

Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as…

Computation and Language · Computer Science 2019-09-12 Marcely Zanon Boito , Aline Villavicencio , Laurent Besacier

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

Computation and Language · Computer Science 2016-10-12 Xiangang Li , Xihong Wu

In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then resynthesize waveform…

Sound · Computer Science 2020-02-06 Jingdong Li , Hui Zhang , Xueliang Zhang , Changliang Li

Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural…

Computation and Language · Computer Science 2017-05-18 Xu Tian , Jun Zhang , Zejun Ma , Yi He , Juan Wei

Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems. Due to their frame-synchronous design, blank symbols are introduced to address the length mismatch between…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-22 Yifan Yang , Xiaoyu Yang , Liyong Guo , Zengwei Yao , Wei Kang , Fangjun Kuang , Long Lin , Xie Chen , Daniel Povey
‹ Prev 1 4 5 6 7 8 10 Next ›