# The third CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines

2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : 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 base-line 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.
Keywords :
Document type :
Conference papers

Cited literature [41 references]

https://hal.inria.fr/hal-01211376
Contributor : Emmanuel Vincent <>
Submitted on : Monday, October 5, 2015 - 9:04:09 AM
Last modification on : Monday, May 4, 2020 - 11:38:40 AM
Long-term archiving on: : Wednesday, January 6, 2016 - 10:27:16 AM

### File

barker_ASRU15.pdf
Files produced by the author(s)

### Identifiers

• HAL Id : hal-01211376, version 1

### Citation

Jon Barker, Ricard Marxer, Emmanuel Vincent, Shinji Watanabe. The third CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines. 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), Dec 2015, Scottsdale, AZ, United States. ⟨hal-01211376⟩

Record views