This paper describes the adaptive multirate wideband (AMR-WB) speech codec selected by the Third Generation Partnership Project (3GPP) for GSM and the third generation mobile communication WCDMA system for providing wideband speech services. The AMR-WB speech codec algorithm was selected in December 2000 and the corresponding specifications were approved in March 2001. The AMR-WB codec was also selected by the International Telecommunication Union-Telecommunication Sector (ITU-T) in July 2001 in the standardization activity for wideband speech coding around 16 kb/s and was approved in January 2002 as Recommendation G.722.2. The adoption of AMR-WB by ITU-T is of significant importance since for the first time the same codec is adopted for wireless as well as wireline services. AMR-WB uses an extended audio bandwidth from 50 Hz to 7 kHz and gives superior speech quality and voice naturalness compared to existing second- and third-generation mobile communication systems. The wideband speech service provided by the AMR-WB codec will give mobile communication speech quality that also substantially exceeds (narrowband) wireline quality. The paper details AMR-WB standardization history, algorithmic description including novel techniques for efficient ACELP wideband speech coding and subjective quality performance of the codec.

The adaptive multirate wideband speech codec (AMR-WB)

Systems and methods for identifying which video segment is being displayed on a screen of a television system. The video segment is identified by deriving data from the television signals, the derived data being indicative of the video segment being displayed on the screen. This feature can be used to extract a viewer's reaction (such as changing the channel) to a specific video segment (such as an advertisement) and reporting the extracted information as metrics. The systems and methods may further provide contextually targeted content to the television system. The contextual targeting is based on not only identification of the video segment being displayed, but also a determination concerning the playing time or offset time of the particular portion of the video segment being currently displayed.

Method for identifying video segments and displaying contextually targeted content on a connected television

In this paper, we propose the regression-based packet loss concealment (PLC) for digital speech transmission by using deep neural networks (DNNs) with a multiple-layer deep architecture. For the DNN training, log-power spectra and phases are employed as features in the input layer for the large training set, which ensures non-linear mapping the frames from the last correctly received frame to the missing frame. Once the training is accomplished by the restricted Boltzmann machine (RBM)-based pre-training to initialize the DNN, minimum mean square error (MMSE)-based fine tuning is then performed based on the back-propagation algorithm. In the reconstruction stage, the trained DNN model is fed with the features of the previous frames in order to estimate the log-power spectra and phases of the missing frames. Reconstruction is further improved by using the cross-fading technique to mitigate discontinuity between the reconstruction signal and good frame signal in the time-domain. To demonstrate the performance of the proposed algorithm, hidden Markov model (HMM)-based PLC algorithm and the PLC algorithm standardized in adaptive multi-rate wideband (AMR-WB) Appendix I were used for comparison. The experimental results show that the proposed approach provides better speech quality and speech recognition accuracy than the conventional approaches.

Packet loss concealment based on deep neural networks for digital speech transmission

Quantization of the linear predictive coding parameters is an important part in speech coding. Probability density function (PDF)-optimized vector quantization (VQ) has been previously shown to be more efficient than VQ based only on training data. For data with bounded support, some well-defined bounded-support distributions (e.g., the Dirichlet distribution) have been proven to outperform the conventional Gaussian mixture model (GMM), with the same number of free parameters required to describe the model. When exploiting both the boundary and the order properties of the line spectral frequency (LSF) parameters, the distribution of LSF differences LSF can be modelled with a Dirichlet mixture model (DMM). We propose a corresponding DMM based VQ. The elements in a Dirichlet vector variable are highly mutually correlated. Motivated by the Dirichlet vector variable's neutrality property, a practical non-linear transformation scheme for the Dirichlet vector variable can be obtained. Similar to the Karhunen-Loeve transform for Gaussian variables, this non-linear transformation decomposes the Dirichlet vector variable into a set of independent beta-distributed variables. Using high rate quantization theory and by the entropy constraint, the optimal inter- and intra-component bit allocation strategies are proposed. In the implementation of scalar quantizers, we use the constrained-resolution coding to approximate the derived constrained-entropy coding. A practical coding scheme for DVQ is designed for the purpose of reducing the quantization error accumulation. The theoretical and practical quantization performance of DVQ is evaluated. Compared to the state-of-the-art GMM-based VQ and recently proposed beta mixture model (BMM) based VQ, DVQ performs better, with even fewer free parameters and lower computational cost

Vector quantization of LSF parameters with a mixture of dirichlet distributions

Immittance spectral pairs (ISPs) form a new set of parameters for representing the linear predictive coding (LPC) filter. For a filter of order n ISP consists of a gain and n-1 frequency parameters, instead of n frequency parameters as is the case for line spectrum pair (LSPs). In regarding LPC as a pseudo-model for the vocal tract, ISP can represent the immitance at the glottis without imposing, like LSP, artificial boundary conditions. In quantization experiments ISP has been found to compare favorably with LSP. A study of interframe differentiation coding for ISP and LSP demonstrates the respective performances of the two sets. >

/pdf/immittance-spectral-pairs-isp-for-speech-encoding-tfouh7etjf.pdf

S. Peller

Papers

Immittance spectral pairs (ISP) for speech encoding