paper-with-me

홈 › Papers

A Bayesian Network View on Acoustic Model-Based Techniques for Robust Speech Recognition

2013-10-11 · Roland Maas, Christian Huemmer, Armin Sehr, Walter Kellermann

This article provides a unifying Bayesian network view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the literature of robust automatic speech recognition. The representatives of these classes can often be deduced from a Bayesian network that extends the conventional hidden Markov models used in speech recognition. These extensions, in turn, can in many cases be motivated from an underlying observation model that relates clean and distorted feature vectors. By converting the observation models into a Bayesian network representation, we formulate the corresponding compensation rules leading to a unified view on known derivations as well as to new formulations for certain approaches. The generic Bayesian perspective provided in this contribution thus highlights structural differences and similarities between the analyzed approaches.

📄 PDF Abstract BibTeX arXiv:1310.3099

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Robust Speech Recognitionspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition

2020-02-24 · Xiaodong Cui, Wei zhang, Ulrich Finkler, George Saon 외

The past decade has witnessed great progress in Automatic Speech Recognition (ASR) due to advances in deep learning. The improvements in performance can be attributed to both improved models and large-scale training data…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Two-Staged Acoustic Modeling Adaption for Robust Speech Recognition by the Example of German Oral History Interviews

2019-08-19 · Michael Gref, Christoph Schmidt, Sven Behnke, Joachim köhler

In automatic speech recognition, often little training data is available for specific challenging tasks, but training of state-of-the-art automatic speech recognition systems requires large amounts of annotated speech. T…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationRobust Speech Recognition+3

Deep Neural Networks for Acoustic Modeling in Speech Recognition

2012-11-01 · Signal Processing Magazine 2012 11 · Geoffrey Hinton, Li Deng, Dong Yu, George Dahl 외

Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models to determine how well each state of each HMM fits a frame or a short wind…

speech-recognitionSpeech Recognition

Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments

2017-05-30 · Zixing Zhang, Jürgen Geiger, Jouni Pohjalainen, Amr El-Desoky Mousa 외

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, incl…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Robust Speech Recognitionspeech-recognition+1

A review of on-device fully neural end-to-end automatic speech recognition algorithms

2020-12-14 · Chanwoo Kim, Dhananjaya Gowda, Dongsoo Lee, Jiyeon Kim 외

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discret…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modeling+4