fMPE: Discriminatively Trained Features for Speech Recognition

Povey, Daniel; Kingsbury, Brian; Mangu, Lidia; Saon, George; Soltau, Hagen; Zweig, Geoffrey

doi:10.1109/icassp.2005.1415275

Cited by 201 publications

(135 citation statements)

References 1 publication

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…In addition to discriminative training, feature transformation based on the discriminative training criterion can be used [11]. This method estimates a matrix M that projects from high-dimensional non-linear features to low-dimensional transformed features, as shown in Eq.…”

Section: Discriminative Feature Transformationmentioning

confidence: 99%

“…Over the past ten years model training techniques have migrated from Maximum Likelihood (ML) estimation to discriminative training [2,3,4,5,6]. In addition, various types of feature transformations have been proposed and showed effectiveness [7,8,9,10,11,12]. Although it is well known that the state-of-the-art ASR techniques are very effective in relatively clean speech conditions, we need further investigation of their effectiveness in challenging conditions such as environmental reverberation and noise.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, we focus on discriminative training and feature transformations for this problem. This paper also deals with several feature transformation approaches, which convert original features to new features based on linear transformations (Linear Discriminant Analysis (LDA) [7], Maximum Likelihood Linear Transformation (MLLT) [8,9], Speaker Adaptive Training (SAT) [10], and discriminative non-linear feature transformation [11,13,14,15,16]). …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Tachioka¹,

Watanabe²,

Hershey³

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2nd Annual Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. ABSTRACT Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2 nd 'CHiME' Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline.

show abstract

Section: Discriminative Feature Transformationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Tachioka¹,

Watanabe²,

Hershey³

2013

2013 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…Over the past 20 years in particular, model training techniques have gradually migrated from maximumlikelihood (ML) estimation approaches to discriminative training techniques [2], [26], [29], [38]. In addition, various types of feature transformations have been proposed [1], [13], [15], [16], [17], [28]. While such state-of-the-art ASR techniques have been shown to be very effective in clean speech conditions, further investigation is needed in order to improve the effectiveness of ASR techniques in challenging conditions such as in the presence of environmental reverberation and noise.…”

Section: Introductionmentioning

confidence: 99%

Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones

Tachioka

Watanabe

Roux

et al. 2017

Journal of Information Processing

View full text Add to dashboard Cite

Reverberant and noisy automatic speech recognition (ASR) using distant stereo microphones is a very challenging, but desirable scenario for home-environment speech applications. This scenario can often provide prior knowledge such as physical information about the sound sources and the environment in advance, which may then be used to reduce the influence of the interference. We propose a method to enhance the binary masking algorithm by using prior distributions of the time difference of arrival. This paper also validates state-of-the-art ASR techniques that include various discriminative training and feature transformation methods. Furthermore, we develop an efficient method to combine discriminative language modeling and minimum Bayes risk decoding in the ASR post-processing stage. We also investigate the effectiveness of this method when used for reverberated and noisy ASR of deep neural networks (DNNs) as well when used in systems that combine multiple DNNs using different features. Experiments on the medium vocabulary sub-task of the second CHiME challenge show that the system submitted to the challenge achieved a 26.86% word error rate (WER), moreover, the DNN system with the discriminative training, speaker adaptation and system combination achieves a 20.40% WER.

show abstract

“…In [3], Rennie et al evaluated one exemplary feature enhancement front-end [4] on a private large scale in-car speech recognition task by using an acoustic model based on fMPE [5] and CMLLR [6].…”

Section: Introductionmentioning

confidence: 99%

Impact of single-microphone dereverberation on DNN-based meeting transcription systems

Yoshioka

Xie

Gales

2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Over the past few decades, a range of front-end techniques have been proposed to improve the robustness of automatic speech recognition systems against environmental distortion. While these techniques are effective for small tasks consisting of carefully designed data sets, especially when used with a classical acoustic model, there has been limited evidence that they are useful for a state-of-theart system with large scale realistic data. This paper focuses on reverberation as a type of distortion and investigates the degree to which dereverberation processing can improve the performance of various forms of acoustic models based on deep neural networks (DNNs) in a challenging meeting transcription task using a single distant microphone. Experimental results show that dereverberation improves the recognition performance regardless of the acoustic model structure and the type of the feature vectors input into the neural networks, providing additional relative improvements of 4.7% and 4.1% to our best configured speaker-independent and speakeradaptive DNN-based systems, respectively.

show abstract

fMPE: Discriminatively Trained Features for Speech Recognition

Cited by 201 publications

References 1 publication

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones

Impact of single-microphone dereverberation on DNN-based meeting transcription systems

Contact Info

Product

Resources

About