Towards a generic approach for automatic speech recognition error detection and classification

System-independent ASR error detection and classification using Recurrent Neural Network

“…A clear motivating example is provided by the exponential growth of black-box speech recognition services, as Google voice Search and automatic captions in Youtube videos, where no information is available about the system used to produce the transcriptions. In this paper, we extends our previous works [5,6] on ASR error detection to a new and different scenario where information about the inner workings of the ASR system is not accessible. Unlike most approaches reported in the literature, we propose to handle the speech recognition errors independently from the decoder's internal information using a set of features derived exclusively from the recognizer output and hence should be trainable for any ASR system.…”

“…ASR errors often are not single events [6]. This is because a miss-recognized word generates often a sequence of ASR errors.…”

Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection

“…Thereby RNN are only able to represent distributions in which the label values are conditionally independent from each other given the input values. ASR errors often are not single events [7]. This is because a miss-recognized word generates often a sequence of ASR errors, as illustrated in Fig.…”

“…To tackle these problems, we have been developing a new approach for ASR error detection and error type classification [3,7,8]. We have targeted a new and different scenario where information about the inner workings of the ASR system is not accessible.…”