Abstract-Several intrusive measures of reverberation can be computed from measured and simulated room impulse responses, over the full frequency band or for each individual mel-frequency subband. It is initially shown that full-band clarity index C50 is the most correlated measure on average with reverberant speech recognition performance. This corroborates previous findings but now for the dataset to be used in this study. We extend the previous findings to show that C50 also exhibits the highest mutual information on average. Motivated by these extended findings, a non-intrusive room acoustic (NIRA) estimation method is proposed to estimate C50 from only the reverberant speech signal. The NIRA method is a data-driven approach based on computing a number of features from the speech signal and it employs these features to train a model used to perform the estimation. The choice of features and learning techniques are explored in this work using an evaluation set which comprises approximately 100000 different reverberant signals (around 93 hours of speech) including reverberation from measured and simulated room impulse responses. The feature importance of each feature with respect to the estimation of the target C50 is analysed following two different approaches. In both cases the newly chosen set of features shows high importance for the target. The best C50 estimator provides a root mean square deviation around 3 dB on average for all reverberant test environments.

Automatic speech recognition in everyday environments must be robust to significant levels of reverberation and noise. One strategy to achieve such robustness is multi-microphone speech enhancement. In this study, we present results of an evaluation of different speech enhancement pipelines using a state-of-the-art ASR system for a wide range of reverberation and noise conditions. The evaluation exploits the recently released ACE Challenge database which includes measured multichannel acoustic impulse responses from 7 different rooms with reverberation times ranging from 0.33 s to 1.34 s. The reverberant speech is mixed with ambient, fan and babble noise recordings made with the same microphone setups in each of the rooms. In the first experiment performance of the ASR without speech processing is evaluated. Results clearly indicate the deleterious effect of both noise and reverberation. In the second experiment, different speech enhancement pipelines are evaluated with relative word error rate reductions of up to 82%. Finally, the ability of selected instrumental metrics to predict ASR performance improvement is assessed. The best performing metric, Short-Time Objective Intelligibility Measure, is shown to have a Pearson correlation coefficient of 0.79, suggesting that it is a useful predictor of algorithm performance in these tests

No abstract

In recent years, a number of automatic detection systems for free-ranging cetaceans have been proposed that aim to detect not just surfaced, but also submerged, individuals. These systems are typically based on pattern-recognition techniques applied to underwater acoustic recordings. Using a Gaussian mixture model, a classification system was developed that detects sounds in recordings and classifies them as one of four types: background noise, whistles, pulses, and combined whistles and pulses. The classifier was tested using a database of underwater recordings made off the Spanish coast during 2011. Using cepstral-coefficient-based parameterization, a sound detection rate of 87.5% was achieved for a 23.6% classification error rate. To improve these results, two parameters computed using the multiple signal classification algorithm and an unpredictability measure were included in the classifier. These parameters, which helped to classify the segments containing whistles, increased the detection rate to 90.3% and reduced the classification error rate to 18.1%. Finally, the potential of the multiple signal classification algorithm and unpredictability measure for estimating whistle contours and classifying cetacean species was also explored, with promising results.

We present single-channel approaches to robust automatic speech recognition (ASR) in reverberant environments based on non-intrusive estimation of the clarity index (C 50 ). Our best performing method includes the estimated value of C 50 in the ASR feature vector and also uses C 50 to select the most suitable ASR acoustic model according to the reverberation level. We evaluate our method on the REVERB Challenge database employing two different C 50 estimators and show that our method outperforms the best baseline of the challenge achieved without unsupervised acoustic model adaptation, i.e. using multi-condition hidden Markov models (HMMs). Our approach achieves a 22.4 % relative word error rate reduction in comparison to the best baseline of the challenge.