Open AccessProceedings Article
Evaluation of the SPLICE algorithm on the Aurora2 database.
Jasha Droppo,Li Deng,Alex Acero +2 more
- pp 217-220
Reads0
Chats0
TLDR
This paper describes recent improvements to SPLICE, Stereo-based Piecewise Linear Compensation for Environments, which produces an estimate of cepstrum of undistorted speech given the observed cepStrum of distorted speech.Abstract:
This paper describes recent improvements to SPLICE, Stereobased Piecewise Linear Compensation for Environments, which produces an estimate of cepstrum of undistorted speech given the observed cepstrum of distorted speech For distributed speech recognition applications, SPLICE can be placed at the server, thus limiting the processing that would take place at the client We evaluated this algorithm on the Aurora2 task, which consists of digit sequences within the TIDigits database that have been digitally corrupted by passing them through a linear filter and/or by adding different types of realistic noises at SNRs ranging from 20dB to -5dB On set A data, for which matched training data is available, we achieved a 66% decrease in word error rate over the baseline system with clean models This preliminary result is of practical significance because in a server implementation, new noise conditions can be added as they are identified once the service is runningread more
Citations
More filters
Book
Application of Hidden Markov Models in Speech Recognition
Mark J. F. Gales,Steve Young +1 more
TL;DR: The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then to describe the various refinements which are needed to achieve state-of-the-art performance.
Journal ArticleDOI
An overview of noise-robust automatic speech recognition
TL;DR: A thorough overview of modern noise-robust techniques for ASR developed over the past 30 years is provided and methods that are proven to be successful and that are likely to sustain or expand their future applicability are emphasized.
Proceedings ArticleDOI
Uncertainty decoding with SPLICE for noise robust speech recognition
Jasha Droppo,Alex Acero,Li Deng +2 more
TL;DR: This paper modifications the SPLICE algorithm to output uncertainty information, and shows that the combination of SPLICE with uncertainty decoding can remove 74.2% of the errors in a subset of the Aurora2 task.
Proceedings ArticleDOI
Mining reference tables for automatic text segmentation
Eugene Agichtein,Venkatesh Ganti +1 more
TL;DR: This paper mine tables present in data warehouses and relational databases to develop an automatic segmentation system that overcome limitations of existing supervised text segmentation approaches, and is robust, accurate, and efficient.
Journal ArticleDOI
Interacting with computers by voice: automatic speech recognition and synthesis
TL;DR: This paper examines how people communicate with computers using speech, and the popular mathematical model called the hidden Markov model (HMM) is examined; first-order HMMs are efficient but ignore long-range correlations in actual speech.
References
More filters
Proceedings Article
The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions
David Pearce,Hans-Günter Hirsch +1 more
TL;DR: A database designed to evaluate the performance of speech recognition algorithms in noisy conditions and recognition results are presented for the first standard DSR feature extraction scheme that is based on a cepstral analysis.
Journal ArticleDOI
Speech recognition in noisy environments: a survey
TL;DR: The survey indicates that the essential points in noisy speech recognition consist of incorporating time and frequency correlations, giving more importance to high SNR portions of speech in decision making, exploiting task-specific a priori knowledge both of speech and of noise, using class-dependent processing, and including auditory models in speech processing.
Speech recognition in noisy environments
TL;DR: It is argued that a careful mathematical formulation of environmental degradation improves recognition accuracy for both data-driven and model-based compensation procedures and shows how the use of vector Taylor series in combination with a Maximum Likelihood formulation produces dramatic improvements in recognition accuracy.
Proceedings ArticleDOI
High-performance robust speech recognition using stereo training data
TL;DR: A novel technique of SPLICE (Stereo-based Piecewise Linear Compensation for Environments) for high performance robust speech recognition is described, an efficient noise reduction and channel distortion compensation technique that makes effective use of stereo training data.
Related Papers (5)
The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions
David Pearce,Hans-Günter Hirsch +1 more