English
Related papers

Related papers: Improving Speaker-Independent Lipreading with Doma…

200 papers

Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when…

Sound · Computer Science 2022-07-26 Kuan Po Huang , Yu-Kuan Fu , Yu Zhang , Hung-yi Lee

Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to…

Computation and Language · Computer Science 2015-09-23 Mortaza Doulaty , Oscar Saz , Thomas Hain

Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-scale data scenarios. However, previous studies focus on…

Sound · Computer Science 2022-11-21 Zhenyu Wang , John H. L. Hansen

For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…

Computation and Language · Computer Science 2020-02-25 Wei-Ning Hsu , Ann Lee , Gabriel Synnaeve , Awni Hannun

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

End-to-end automatic speech recognition (E2E ASR) systems have significantly improved speech recognition through training on extensive datasets. Despite these advancements, they still struggle to accurately recognize domain specific words,…

Computation and Language · Computer Science 2024-07-26 Jiwon Suh , Injae Na , Woohwan Jung

Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem,…

Computation and Language · Computer Science 2018-06-14 Hao Tang , Wei-Ning Hsu , Francois Grondin , James Glass

Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Ze Li , Yao Shi , Yunfei Xu , Ming Li

The teacher-student (T/S) learning has been shown effective in unsupervised domain adaptation [1]. It is a form of transfer learning, not in terms of the transfer of recognition decisions, but the knowledge of posteriori probabilities in…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-01 Zhong Meng , Jinyu Li , Yifan Gong , Biing-Hwang , Juang

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

Machine Learning · Computer Science 2015-09-18 Mortaza Doulaty , Oscar Saz , Thomas Hain

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

Computation and Language · Computer Science 2017-08-21 Jinyu Li , Michael L. Seltzer , Xi Wang , Rui Zhao , Yifan Gong

Many consumer speech recognition systems are not tuned for people with speech disabilities, resulting in poor recognition and user experience, especially for severe speech differences. Recent studies have emphasized interest in personalized…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Colin Lea , Dianna Yee , Jaya Narain , Zifang Huang , Lauren Tooley , Jeffrey P. Bigham , Leah Findlater

Lipreading is the task of decoding text from the movement of a speaker's mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction. More recent deep lipreading approaches are…

Machine Learning · Computer Science 2016-12-19 Yannis M. Assael , Brendan Shillingford , Shimon Whiteson , Nando de Freitas

In this paper we proposed a novel Adversarial Training (AT) approach for end-to-end speech recognition using a Criticizing Language Model (CLM). In this way the CLM and the automatic speech recognition (ASR) model can challenge and learn…

Computation and Language · Computer Science 2018-11-05 Alexander H. Liu , Hung-yi Lee , Lin-shan Lee

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Computation and Language · Computer Science 2024-03-28 Brian Formento , Wenjie Feng , Chuan Sheng Foo , Luu Anh Tuan , See-Kiong Ng

Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers. However, synthesizing a new…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Byoung Jin Choi , Myeonghun Jeong , Minchan Kim , Sung Hwan Mun , Nam Soo Kim

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…

Audio and Speech Processing · Electrical Eng. & Systems 2021-03-11 Nilaksh Das , Sravan Bodapati , Monica Sunkara , Sundararajan Srinivasan , Duen Horng Chau

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based…

Computation and Language · Computer Science 2021-02-17 Sameer Khurana , Niko Moritz , Takaaki Hori , Jonathan Le Roux

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Sound · Computer Science 2022-03-29 Xichen Pan , Peiyu Chen , Yichen Gong , Helong Zhou , Xinbing Wang , Zhouhan Lin

Sound event detection systems are widely used in various applications such as surveillance and environmental monitoring where data is automatically collected, processed, and sent to a cloud for sound recognition. However, this process may…

Sound · Computer Science 2024-01-04 Shayan Gharib , Minh Tran , Diep Luong , Konstantinos Drossos , Tuomas Virtanen