Refine
Document Type
- conference proceeding (article) (2)
- Article (1)
- Part of a Book (1)
Language
- English (4)
Has Fulltext
- no (4)
Is part of the Bibliography
- no (4)
Keywords
- Reverberation (2)
- Automatic speech recognition (1)
- Dereverberation (1)
- Evaluation campaign (1)
- Hidden Markov models (1)
- QUALITY (1)
- REVERB challenge (1)
- Speech (1)
- Speech processing (1)
- Speech recognition (1)
Institute
Begutachtungsstatus
- peer-reviewed (1)
The REVERB challenge is a benchmark task designed to evaluate reverberation-robust automatic speech recognition techniques under various conditions. A particular novelty of the REVERB challenge database is that it comprises both real reverberant speech recordings and simulated reverberant speech, both of which include tasks to evaluate techniques for 1-, 2-, and 8-microphone situations. In this chapter, we describe the problem of reverberation and characteristics of the REVERB challenge data, and finally briefly introduce some results and findings useful for reverberant speech processing in the current deep-neural-network era.
This paper overviews the state of the art in reverberant speech processing from the speech recognition viewpoint. First, it points out that the key to successful reverberant speech recognition is to account for long-term dependencies between reverberant observations obtained from consecutive time frames. Then, a diversity of approaches that exploit the long-term dependencies in various ways is described, ranging from signal and feature dereverberation to acoustic model compensation tailored to reverberation. A framework for classifying those approaches is presented to highlight similarities and differences between them.
A novel framework based on conditional emission densities for
hidden Markov models (HMMs) is proposed in this contribution to integrate speech enhancement systems with automatic speech recognition systems. In the training phase, the observed feature vectors, corrupted by background noise and reverberation, together with estimates for the interference as provided by the speech enhancement system are used for training joint densities of the observations and the interference estimates. In the decoding phase, the joint densities are transformed to conditional densities of the observed features given the interference estimates.
Thus, front end processing can be exploited for obtaining interference estimates, and the estimation errors can be modeled very effectively in a data-driven way. Connected digit recognition experiments in a simulated reverberant environment show the potential of the proposed approach: HMMs with the proposed conditional densities outperform various configurations of conventional HMMs in the logarithmic melspectral domain. This is a first step towards using conditional densities for creating synergies between front end and back end.
Index Terms: speech enhancement, robust speech recognition,
dereverberation, conditional HMM emission densities, frame-
by-frame model adaptation.
In recent years, 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 that are robust to reverberation. In this paper, we describe the REVERB challenge, which is an evaluation campaign that was designed to evaluate such speech enhancement (SE) and ASR techniques to reveal the state-of-the-art techniques and obtain new insights regarding potential future research directions. Even though most existing benchmark tasks and challenges for distant speech processing focus on the noise robustness issue and sometimes only on a single- channel scenario, a particular novelty of the REVERB challenge is that it is carefully designed to test robustness against reverberation, based on both real, single- channel, and multichannel recordings. This challenge attracted 27 papers, which represent 25 systems specifically designed for SE purposes and 49 systems specifically designed for ASR purposes. This paper describes the problems dealt within the challenge, provides an overview of the submitted systems, and scrutinizes them to clarify what current processing strategies appear effective in reverberant speech processing.