Multi-microphone correlation-based processing for robust speech recognition

We present a new array processing algorithm for microphone array speech recognition. Conventionally, the goal of array processing is to take distorted signals captured by the array and generate a cleaner output waveform. However, speech recognition systems operate on a set of features derived from the waveform, rather than the waveform itself. The goal of an array processor used in conjunction with a recognition system is to generate a waveform which produces a set of recognition features which maximize the likelihood for the words that are spoken, rather than to minimize the waveform distortion. We propose a new array processing algorithm which maximizes the likelihood of the recognition features. This is accomplished through the use of a new objective function which utilizes information from the recognition system itself, obtained in an unsupervised manner, to optimize the parameters of a filter-and-sum array processor. Using the proposed method, improvements in word error rate of up to 36% over conventional methods are achieved on real microphone array tasks in a wide range of environments.

show abstract

“…Experiments were performed using two real microphone array databases recorded at CMU [5], to evaluate the algorithm proposed.…”

Section: Resultsmentioning

confidence: 99%

Speech recognizer-based microphone array processing for robust hands-free speech recognition

Seltzer

Raj

Stern

2002

IEEE International Conference on Acoustics Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…However, this procedure can be impractical because such measurements may have to be repeated frequently in order to track a changing channel. Reverberations can also be combated with even more elaborate (and more cumbersome) methods involving microphone arrays 6 .…”

Section: B Conventional Methods Of Achieving Channel-independent Asrmentioning

confidence: 99%

Blind normalization of speech from different channels

Levin

2004

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

We show how to construct a channel-independent representation of speech that has propagated through a noisy reverberant channel. This is done by blindly rescaling the cepstral time series by a non-linear function, with the form of this scale function being determined by previously encountered cepstra from that channel. The rescaled form of the time series is an invariant property of it in the following sense: it is unaffected if the time series is transformed by any time-independent invertible distortion.Because a linear channel with stationary noise and impulse response transforms cepstra in this way, the new technique can be used to remove the channel dependence of a cepstral time series. In experiments, the method achieved greater channelindependence than cepstral mean normalization, and it was comparable to the combination of cepstral mean normalization and spectral subtraction, despite the fact that no measurements of channel noise or reverberations were required (unlike spectral subtraction).

show abstract

“…The longest width of 40 cm was determined by the width of the dashboard. Such an inhomogeneous arrangement can also be found in [17]. These microphones were labeled as #1 to #7 from the driver's side to the window's side, so #4 is the central microphone.…”

Section: Hitnavi05mentioning

confidence: 99%

Multi-Input Feature Combination in the Cepstral Domain for Practical Speech Recognition Systems

Obuchi

Hataoka

2009

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this paper we describe a new framework of feature combination in the cepstral domain for multi-input robust speech recognition. The general framework of working in the cepstral domain has various advantages over working in the time or hypothesis domain. It is stable, easy to maintain, and less expensive because it does not require precise calibration. It is also easy to configure in a complex speech recognition system. However, it is not straightforward to improve the recognition performance by increasing the number of inputs, and we introduce the concept of variance re-scaling to compensate the negative effect of averaging several input features. Finally, we propose to take another advantage of working in the cepstral domain. The speech can be modeled using hidden Markov models, and the model can be used as prior knowledge. This approach is formulated as a new algorithm, referred to as Hypothesis-Based Feature Combination. The effectiveness of various algorithms are evaluated using two sets of speech databases. We also refer to automatic optimization of some parameters in the proposed algorithms.

show abstract

Multi-microphone correlation-based processing for robust speech recognition

Cited by 35 publications

References 10 publications

Speech recognizer-based microphone array processing for robust hands-free speech recognition

Speech recognizer-based microphone array processing for robust hands-free speech recognition

Blind normalization of speech from different channels

Multi-Input Feature Combination in the Cepstral Domain for Practical Speech Recognition Systems

Contact Info

Product

Resources

About