scispace - formally typeset
Proceedings ArticleDOI

The reverb challenge: Acommon evaluation framework for dereverberation and recognition of reverberant speech

Reads0
Chats0
TLDR
A common evaluation framework including datasets, tasks, and evaluation metrics for both speech enhancement and ASR techniques is proposed, which will be used as a common basis for the REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge.
Abstract
Recently, substantial progress has been made in the field of reverberant speech signal processing, including both single- and multichannel dereverberation techniques, and automatic speech recognition (ASR) techniques robust to reverberation. To evaluate state-of-the-art algorithms and obtain new insights regarding potential future research directions, we propose a common evaluation framework including datasets, tasks, and evaluation metrics for both speech enhancement and ASR techniques. The proposed framework will be used as a common basis for the REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge. This paper describes the rationale behind the challenge, and provides a detailed description of the evaluation framework and benchmark results.

read more

Citations
More filters
Proceedings ArticleDOI

A study on data augmentation of reverberant speech for robust speech recognition

TL;DR: It is found that the performance gap between using simulated and real RIRs can be eliminated when point-source noises are added, and the trained acoustic models not only perform well in the distant- talking scenario but also provide better results in the close-talking scenario.
Journal ArticleDOI

An analysis of environment, microphone and data simulation mismatches in robust speech recognition

TL;DR: It is found that training on different noise environments and different microphones barely affects the ASR performance, especially when several environments are present in the training data: only the number of microphones has a significant impact.
Proceedings ArticleDOI

Improved MVDR beamforming using single-channel mask prediction networks

TL;DR: It is shown that using a single mask across microphones for covariance prediction with minima-limited post-masking yields the best result in terms of signal-level quality measures and speech recognition word error rates in a mismatched training condition.
Proceedings ArticleDOI

A learning-based approach to direction of arrival estimation in noisy and reverberant environments

TL;DR: A learning-based approach that can learn from a large amount of simulated noisy and reverberant microphone array inputs for robust DOA estimation and uses a multilayer perceptron neural network to learn the nonlinear mapping from such features to the DOA.
References
More filters
Proceedings Article

The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions

TL;DR: A database designed to evaluate the performance of speech recognition algorithms in noisy conditions and recognition results are presented for the first standard DSR feature extraction scheme that is based on a cepstral analysis.
Book

Spoken Language Processing: A Guide to Theory, Algorithm, and System Development

TL;DR: Spoken Language Processing draws on the latest advances and techniques from multiple fields: computer science, electrical engineering, acoustics, linguistics, mathematics, psychology, and beyond to create the state of the art in spoken language technology.
Journal ArticleDOI

Evaluation of Objective Quality Measures for Speech Enhancement

TL;DR: The evaluation of correlations of several objective measures with these three subjective rating scales is reported on and several new composite objective measures are also proposed by combining the individual objective measures using nonparametric and parametric regression analysis techniques.
Book

Speech Dereverberation

TL;DR: Speech Dereverberation presents the most important current approaches to the problem of reverberation and defines the current state of the art and encourages further work on this topic by offering open research questions to exercise the curiosity of the reader.
Related Papers (5)