English
Related papers

Related papers: Enhanced Hybrid Transducer and Attention Encoder D…

200 papers

Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

Sound · Computer Science 2021-05-11 Shakti Kumar , Jithin Pradeep , Hussain Zaidi

Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set…

Computation and Language · Computer Science 2022-09-14 Kartik Audhkhasi , Yinghui Huang , Bhuvana Ramabhadran , Pedro J. Moreno

Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not…

Computation and Language · Computer Science 2023-06-16 Zheng Liang , Zheshu Song , Ziyang Ma , Chenpeng Du , Kai Yu , Xie Chen

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-12 Keqi Deng , Philip C. Woodland

Learning effective sentence representations is crucial for many Natural Language Processing (NLP) tasks, including semantic search, semantic textual similarity (STS), and clustering. While multiple transformer models have been developed for…

Computation and Language · Computer Science 2023-11-30 Liya Wang , Jason Chou , Dave Rouck , Alex Tien , Diane M Baumgartner

In this work, we tackle the Diacritic Restoration (DR) task for Arabic dialectal sentences using a multimodal approach that combines both textual and speech information. We propose a model that represents the text modality using an encoder…

Computation and Language · Computer Science 2025-10-29 Ahmad Ghannam , Naif Alharthi , Faris Alasmary , Kholood Al Tabash , Shouq Sadah , Lahouari Ghouti

Context cues carry information which can improve multi-turn interactions in automatic speech recognition (ASR) systems. In this paper, we introduce a novel mechanism inspired by hyper-prompting to fuse textual context with acoustic…

Computation and Language · Computer Science 2024-01-17 Sergio Duarte-Torres , Arunasish Sen , Aman Rana , Lukas Drude , Alejandro Gomez-Alanis , Andreas Schwarz , Leif Rädel , Volker Leutnant

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Sound · Computer Science 2022-07-05 Kun Wei , Pengcheng Guo , Ning Jiang

In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in…

Computation and Language · Computer Science 2025-03-19 Wuwei Huang , Dexin Wang , Deyi Xiong

We propose a new end-to-end neural diarization (EEND) system that is based on Conformer, a recently proposed neural architecture that combines convolutional mappings and Transformer to model both local and global dependencies in speech. We…

Computation and Language · Computer Science 2022-02-22 Yi Chieh Liu , Eunjung Han , Chul Lee , Andreas Stolcke

The rapid development of single-modal pre-training has prompted researchers to pay more attention to cross-modal pre-training methods. In this paper, we propose a unified-modal speech-unit-text pre-training model, SpeechUT, to connect the…

Computation and Language · Computer Science 2022-10-10 Ziqiang Zhang , Long Zhou , Junyi Ao , Shujie Liu , Lirong Dai , Jinyu Li , Furu Wei

We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers for end-to-end automatic speech recognition. The first…

Computation and Language · Computer Science 2019-11-12 Zhong Meng , Yashesh Gaur , Jinyu Li , Yifan Gong

Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attention-based models cannot be used in online speech recognition,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-24 Jian Luo , Jianzong Wang , Ning Cheng , Jing Xiao

Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating…

Computation and Language · Computer Science 2023-05-24 Tian-Hao Zhang , Hai-Bo Qin , Zhi-Hao Lai , Song-Lu Chen , Qi Liu , Feng Chen , Xinyuan Qian , Xu-Cheng Yin

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-27 Mingyu Cui , Jiawen Kang , Jiajun Deng , Xi Yin , Yutao Xie , Xie Chen , Xunying Liu

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data…

Computation and Language · Computer Science 2024-11-05 Chenpeng Du , Hao Li , Yizhou Lu , Lan Wang , Yanmin Qian

End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain…

Computation and Language · Computer Science 2023-02-23 Jiaming Zhou , Shiwan Zhao , Ning Jiang , Guoqing Zhao , Yong Qin

This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech. Most existing algorithms rely on paired dry/wet data, which is difficult to obtain, or…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-12 Louis Bahrman , Mathieu Fontaine , Gael Richard

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe
‹ Prev 1 8 9 10 Next ›