Speech Analysis for Automatic Speech Recognition (ASR) systems typically starts with a Short-Time Fourier Transform (STFT) that implies selecting a fixed point in the time-frequency resolution trade-off. This approach, combined with a Mel-frequency scaled filterbank and a Discrete Cosine Transform give rise to the Mel-Frequency Cepstral Coefficients (MFCC), which have been the most common speech features in speech processing for the last decades. These features were particularly well suited for the previous Hidden Markov Models/Gaussian Mixture Models (HMM/GMM) state of the art in ASR. In particular they produced highly uncorrelated features of small dimensionality (typically 13 coefficients plus deltas and double deltas), which was very convenient for diagonal covariance GMMs, for dealing with the curse of dimensionality and for the limited computing resources of a decade ago. Currently most ASR systems use Deep Neural Networks (DNN) instead of the GMMs for modeling the acoustic features, which provides more flexibility regarding the definition of the features. In particular, acoustic features can be highly correlated and can be much larger in size because the DNNs are very powerful at processing high-dimensionality inputs. Also, the computing hardware has reached a level of evolution that makes computational cost in speech processing a less relevant issue. In this context we have decided to revisit the problem of the time-frequency resolution in speech analysis, and in particular to check if multi-resolution speech analysis (both in time and frequency) can be helpful in improving acoustic modeling using DNNs. Our experiments start with several Kaldi baseline system for the well known TIMIT corpus and modify them by adding multi-resolution speech representations by concatenating different spectra computed using different time-frequency resolutions and different post-processed and speaker-adapted features using different time-frequency resolutions. Our experiments show that using a multi-resolution speech representation tends to improve over results using the baseline single resolution speech representation, which seems to confirm our main hypothesis. However, results combining multi-resolution with the highly post-processed and speaker-adapted features, which provide the best results in Kaldi for TIMIT, yield only very modest improvements.

Client conversations in contact centers are nowadays routinely recorded for a number of reasons—in many cases, just because it is required by current legislation. However, even if not required, conversations between customers and agents can be a valuable source of information about clients or future clients, call center agents, markets trends, etc. Analyzing these recordings provides an excellent opportunity to be aware about the business and its possibilities. The current state of the art in Automatic Speech Recognition (ASR) allows this information to be effectively extracted and used. However, conversations are usually stored in highly compressed ways to save space and typically contain packet losses that produce short interruptions in the speech signal due to the common use of Voice-over-IP (VoIP) in these systems. These effects, and especially the last one, have a negative impact on ASR performance. This article presents an extensive study on the importance of these effects on modern ASR systems and the effectiveness of using several techniques of data augmentation to increase their robustness. In addition, ITU-T G.711, a well-known Packet Loss Concealment (PLC) method is applied in combination with data augmentation techniques to analyze ASR performance improvement on signals affected by packet losses.

(1) Background: As far back as the 1930s, it was already thought that gestures, clothing, speech, posture, and gait could express an individual’s personality. Different research programs, some focused on linguistic cues, were launched, though results were inconsistent. The development of new speech analysis technology and the generalization of big data analysis have created an opportunity to test the predictive power of voice features on personality dimensions. This study aims to explore the feasibility of an automatic personality assessment system in the context of personnel selection. (2) Methods: One hundred participants were recorded during an individual interview for voice analysis. They also completed the NEO-FFI and were required to ask and collect the assessment of their personality by a close significant other. Furthermore, an expert estimated participants’ personality dimensions based on the viewing of the recorded interviews. (3) Results: Results showed there are specific voice features related to the externalization of individuals’ personalities (predictions ranging from 0.3 to 0.4). Voice features also predicted significant others’ estimations and expert ratings of the target individual’s personality, though the features were not exactly the same. (4) Conclusions: It is noteworthy that predictions were made based on voice recordings obtained using ordinary devices in controlled but not restricted speech situations, which may make such an approach a promising tool for personality assessment in contexts such as personnel selection.