Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME challenge results

Pfeifenberger, Lukas; Schrank, Tobias; Zöhrer, Matthias; Hagmüller, Martín; Pernkopf, Franz

doi:10.1109/asru.2015.7404830

Cited by 10 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This step was taken by most of the top scoring teams and appears to have been important for success. Rescoring was performed using either a DNN-LM [25], LSTM-LM [40] or most commonly an recurrent neural network language model (RNN-LM) [18,21,31,38]. Some teams using RNN-LM rescoring also increased the context of the 3-gram model, replacing it with a 4-gram [29,32] or 5-gram [19].…”

Section: Statistical Modelingmentioning

confidence: 99%

The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines

Barker

Marxer

Vincent

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

533

443

View full text Add to dashboard Cite

The CHiME challenge series aims to advance far field speech recognition technology by promoting research at the interface of signal processing and automatic speech recognition. This paper presents the design and outcomes of the 3rd CHiME Challenge, which targets the performance of automatic speech recognition in a real-world, commercially-motivated scenario: a person talking to a tablet device that has been fitted with a six-channel microphone array. The paper describes the data collection, the task definition and the baseline systems for data simulation, enhancement and recognition. The paper then presents an overview of the 26 systems that were submitted to the challenge focusing on the strategies that proved to be most successful relative to the MVDR array processing and DNN acoustic modeling reference system. Challenge findings related to the role of simulated data in system training and evaluation are discussed.

show abstract

Section: Statistical Modelingmentioning

confidence: 99%

The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines

Barker

Marxer

Vincent

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

533

443

View full text Add to dashboard Cite

show abstract

“…All teams doing so were able to achieve significant performance enhancements. Language models used for rescoring included DNN-LMs [34], LSTM-LMs [10] or, most commonly, recurrent neural network language models (RNN-LMs) [36,27,28,22].…”

Section: Strategies For Improved Statistcal Modellingmentioning

confidence: 99%

The CHiME Challenges: Robust Speech Recognition in Everyday Environments

Barker

Marxer

Watanabe

2017

New Era for Robust Speech Recognition

View full text Add to dashboard Cite

The CHiME challenge series has been aiming to advance the development of robust automatic speech recognition for use in everyday environments by encouraging research at the interface of signal processing and statistical modelling. The series has been running since 2011 and is now entering its 4th iteration. This chapter provides an overview of the CHiME series including a description of the datasets that have been collected and the tasks that have been defined for each edition. In particular the chapter describes novel approaches that have been developed for producing simulated data for system training and evaluation, and conclusions about the validity of using simulated data for robust speech recognition development. We also provide a brief overview of the systems and specific techniques that have proved successful for each task. These systems have demonstrated the remarkable robustness that can be achieved through a combination of training data simulation and multicondition training, well-engineered multichannel enhancement and state-of-the-art discriminative acoustic and language modelling techniques.

show abstract

“…The performance of an automatic speech recognition (ASR) system may degrade significantly in noisy environments. Microphone array beamforming has shown great potential in improving ASR performance in noise [1,2,3,4,5]. A beamformer is often parameterized by a steering vector (SV) for a target direction, as with delay-and-sum beamforming and minimum variance distortionless response (MVDR) beamforming.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method to Correct Steering Vectors in MVDR Beamformer for Noise Robust ASR

Zhao

Hwang³

2019

Interspeech 2019

View full text Add to dashboard Cite

Accurate steering vectors (SV) are key to many beamformers. However, reliable SV is not easy to obtain. In this work, we investigate a novel method to identify and correct phase errors in SV for MVDR beamforming. Our idea stems from the linear relationship in the phase of a microphone component in narrowband SVs across frequency, as modeled by acoustic transfer function. We utilize this property and feedforward neural nets to make phase prediction for the microphone components in SVs, and use the predicted phase selectively for phase error correction and MVDR beamforming. Our method is robust to large fluctuations in phase spectrum wrapped within [−π, π]. We have evaluated our approach on CHiME-3 and obtained improved performances on both word error rate and short-time objective intelligibility in low reverberant acoustic environments.

show abstract

Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME challenge results

Cited by 10 publications

References 20 publications

The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines

The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines

The CHiME Challenges: Robust Speech Recognition in Everyday Environments

A Novel Method to Correct Steering Vectors in MVDR Beamformer for Noise Robust ASR

Contact Info

Product

Resources

About