Statistics based features for unvoiced sound classification

Spectral and textural features for automatic classification of fricatives

Abstract: Classification of unvoiced fricatives is an important stage in applications such as spoken term detection and audio-video synchronization, and in technologies for the hearing impaired Due to their acoustic similarity, extraction of multiple features and construction of high-dimensional feature vectors are required for successful classification of these phonemes In this study two dimensionality reduction algorithms, namely, t-distributed Stochastic Neighbor Embedding (t-SNE) and Sequential Forward Floating Selection (SFFS) were used to obtain a compact representation of the data A classification stage (kNN or SVM) was then applied, in which we compared the identification rates between the original feature vector and the low-dimensional representation A total of 1000 unvoiced fricatives (/s/ /sh/ /f/ and /th/) derived from the TIMIT speech database, containing 25000 short frames of 8 ms each, were used for the evaluation We show that representing the data by a feature vector with as few as 3 dimensions, yields a classification rate of almost 90% which outperforms most of the results obtained in previous studies

Online forecasting method for high-frequency mechanical noise of structure

Abstract: The invention discloses an online forecasting method for high-frequency mechanical noise of a structure, and belongs to the technical field of noise forecasting. The method comprises the following steps: building a reasonable and effective constraint and load statistical energy analysis model aiming at an engineering practice structure; obtaining quality data of various stimulated sub-systems by the built statistical energy analysis model; testing vibration response data of the stimulated sub-systems through a test; calculating energy data of the stimulated sub-systems by combining the quality data with the response data; obtaining radiated sound power energy mechanical mobility data corresponding to the stimulated sub-systems according to the model; and finally calculating the radiated sound power of the structure, and finishing online forecasting. The online forecasting method has the beneficial effects that rapid calculation from load to radiated sound power is achieved by the system transfer mobility invariability; the problem of relatively long elapsed time of the traditional algorithm is solved; and rapid forecasting of mechanical noise of the structure is achieved. The online forecasting method is considerable in accuracy and relatively short in elapsed time, can be applied to the online forecasting engineering practice, and has a wide application prospect.

A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting

Abstract: In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone?Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in Rn. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.

Sound Texture Perception via Statistics of the Auditory Periphery: Evidence from Sound Synthesis

Abstract: SUMMARY Rainstorms, insect swarms, and galloping horses produce ‘‘sound textures’’—the collective result of many similar acoustic events. Sound textures are distinguished by temporal homogeneity, suggesting they could be recognized with time-averaged statistics. To test this hypothesis,we processed real-world textures with an auditory model containing filters tuned for sound frequencies and their modulations, and measured statistics of the resulting decomposition. We then assessed the realism and recognizability of novel sounds synthesized to have matching statistics. Statistics of individual frequency channels, capturing spectral power and sparsity, generally failedtoproduce compellingsynthetictextures;however, combining them with correlations between channels produced identifiable and natural-sounding textures. Synthesis quality declined if statistics were computed from biologically implausible auditory models. The results suggest that sound texture perception is mediated by relatively simple statistics of early auditory representations, presumably computed by downstream neural populations. The synthesis methodology offers a powerful tool for their further investigation.

Segregation of unvoiced speech from nonspeech interference

Abstract: Monaural speech segregation has proven to be extremely challenging. While efforts in computational auditory scene analysis have led to considerable progress in voiced speech segregation, little attention has been given to unvoiced speech, which lacks harmonic structure and has weaker energy, hence more susceptible to interference. This study proposes a new approach to the problem of segregating unvoiced speech from nonspeech interference. The study first addresses the question of how much speech is unvoiced. The segregation process occurs in two stages: Segmentation and grouping. In segmentation, the proposed model decomposes an input mixture into contiguous time-frequency segments by a multiscale analysis of event onsets and offsets. Grouping of unvoiced segments is based on Bayesian classification of acoustic-phonetic features. The proposed model for unvoiced speech segregation joins an existing model for voiced speech segregation to produce an overall system that can deal with both voiced and unvoiced speech. Systematic evaluation shows that the proposed system extracts a majority of unvoiced speech without including much interference, and it performs substantially better than spectral subtraction.

Acoustic-phonetic features for the automatic classification of fricatives

Abstract: In this article, the acoustic-phonetic characteristics of the American English fricative consonants are investigated from the automatic classification standpoint. The features studied in the literature are evaluated and new features are proposed. To test the value of the extracted features, a statistically guided, knowledge-based, acoustic-phonetic system for the automatic classification of fricatives in speaker-independent continuous speech is proposed. The system uses an auditory-based front-end processing system and incorporates new algorithms for the extraction and manipulation of the acoustic-phonetic features that proved to be rich in their information content. Classification experiments are performed using hard-decision algorithms on fricatives extracted from the TIMIT database continuous speech of 60 speakers (not used in the design/training process) from seven different dialects of American English. An accuracy of 93% is obtained for voicing detection, 91% for place of articulation detection, and 87% for the overall classification of fricatives.