The PASCAL CHiME speech separation and recognition challenge

Abstract

Distant microphone speech recognition systems that operate with humanlike robustness remain a distant goal. The key difficulty is that operating in everyday listening conditions entails processing a speech signal that is reverberantly mixed into a noise background composed of multiple competing sound sources. This paper describes a recent speech recognition evaluation that was designed to bring together researchers from multiple communities in order to foster novel approaches to this problem. The task was to identify keywords from sentences reverberantly mixed into audio backgrounds binaurally-recorded in a busy domestic environment. The challenge was designed to model the essential difficulties of multisource environment problem while remaining on a scale that would make it accessible to a wide audience. Compared to previous ASR evaluation a particular novelty of the task is that the utterances to be recognised were provided in a continuous audio background rather than as pre-segmented utterances thus allowing a range of background modelling techniques to be employed. The challenge attracted thirteen submissions. This paper describes the challenge problem, provides an overview of the systems that were entered and provides a comparison alongside both a baseline recognition system and human performance. The paper discusses insights gained from the challenge and lessons learnt for the design of future such evaluations.

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

“…Regarding ASR, the variation of the word error rate (WER) as a function of the SNR was studied in several evaluation challenges, e.g., (Hirsch and Pearce, 2000;Barker et al, 2013). The adaptation of DNN acoustic models to specific acoustic conditions has been investigated, e.g., (Seltzer et al, 2013;Karanasou et al, 2014), however it has been evaluated in multi-condition settings rather than actual mismatched conditions.…”

Investigation and Development of Methods for Improving Robustness of Automatic Speech Recognition Algorithms in Complex Acoustic Environments

“…Development of such processing methods is especially important for the applications like "smart home" when microphones are located in several parts of the room and both location and orientation of speaker's head are unknown in advance. In order to promote the development of multi-microphone approaches in robust speech recognition, several international competitions like CHiME (Computational Hearing in Multisource Environments) Challenge [6][7][8][9] have been organized in recent years.…”

Spectral and Cepstral Audio Noise Reduction Techniques in Speech Emotion Recognition

“…This step was performed to simulate talking over a smartphone in di↵erent places. Di↵erent types of additive noise were then added, using the CHiME-2013 database [1] for simulating a living room environment (CHiME ), and data collected from the freesound platform 1 to simulate public transport (trains) environments. We collected, in total, 230 minutes of noise, to match the duration of the RECOLA database.…”