Linear predictive coding

About: Linear predictive coding is a research topic. Over the lifetime, 6565 publications have been published within this topic receiving 142991 citations. The topic is also known as: Linear predictive coding, LPC.

System and method for retrieving and presenting speech information

Abstract: In the method, speech files each representing speech information are provided. At least one of the speech files is a hyperspeech file that represents speech information and includes a hot spot specification specifying a hot spot in the speech information. The hot spot identifies additional speech information. The hot spot specification comprises a hot spot definition defining the hot spot and an identifier identifying another of the speech files that represents the additional speech information. A speech information presentation operation is iteratively performed until the desired speech information is presented. In this operation, a speech file retrieval operation that retrieves one of the speech files is performed, any hot spot specification in the speech file is extracted, a speech signal is generated from the speech file, and the speech information is presented in response to the speech signal. The speech signal includes a distinguishing portion that distinguishes each hot spot from the remainder of the speech information when the speech information is presented. When the speech information presented is not the desired speech information, a user request signal is provided during the hot spot to request presentation of the additional speech information identified by the speech information presented during the hot spot. The identifier included in the hot spot specification is referenced in response to the user request signal. The identifier identifies the speech file to be retrieved when the speech file retrieval operation is next performed.

A linear predictive front-end processor for speech recognition in noisy environments

Abstract: We investigate the performance of a recent algorithm for linear predictive (LP) modeling of speech signals, which have been degraded by uncorrelated additive noise, as a front-end processor in a speech recognition system. The system is speaker dependent, and recognizes isolated words, based on dynamic time warping principles. The LP model for the clean speech is estimated through appropriate composite modeling of the noisy speech. This is done by minimizing the Itakura-Saito distortion measure between the sample spectrum of the noisy speech and the power spectral density of the composite model. This approach results in a "filtering-modeling" scheme in which the filter for the noisy speech, and the LP model for the clean speech, are alternatively optimized. The proposed system was tested using the 26 word English alphabet, the ten English digits, and the three command words, "stop," "error," and "repeat," which were contaminated by additive white noise at 5-20 dB signal to noise ratios (SNR's). By replacing the standard LP analysis with the proposed algorithm, during training on the clean speech and testing on the noisy speech, we achieve an improvement in recognition accuracy equivalent to an increase in input SNR of approximately 10 dB.

Microprocessor realization of a linear predictive vocoder

Abstract: A microprocessor realization for a linear predictive vocoder is presented. The goal was a low-power, low-cost, compact special-purpose realization of a narrow-band speech terminal. The resultant design is a general-purpose two-bus structure running at a 150 ns cycle time, using as the basic signal processing element, four of the AMD 2901 CPE chips. This basic structure is augmented by a four-cycle multiplier to allow for sufficient signal processing power. The design concessions that mark the linear predictive coding microprocessor (LPCM) as a special-purpose machine designed to be a speech terminal are: limited I/O and limited memory. The present design requires 162 dual-in-line packages, dissipates less than 45 W and occupies about \frac{1}{3} ft3.

Phoneme-specific speech separation

Abstract: Speech separation or enhancement algorithms seldom exploit information about phoneme identities. In this study, we propose a novel phoneme-specific speech separation method. Rather than training a single global model to enhance all the frames, we train a separate model for each phoneme to process its corresponding frames. A robust ASR system is employed to identify the phoneme identity of each frame. This way, the information from ASR systems and language models can directly influence speech separation by selecting a phoneme-specific model to use at the test stage. In addition, phoneme-specific models have fewer variations to model and do not exhibit the data imbalance problem. The improved enhancement results can in turn help recognition. Experiments on the corpus of the second CHiME speech separation and recognition challenge (task-2) demonstrate the effectiveness of this method in terms of objective measures of speech intelligibility and quality, as well as recognition performance.

Predictive coding of speech using analysis-by-synthesis techniques

Abstract: This paper presents an overview of analysis-by-synthesis techniques used for low bit rate coding of speech signals. Analysis-by-synthesis procedures use linear predictors to remove the redundancies in the speech signal. The remaining difference signal is not quantized directly, but is replaced by an excitation signa1 that can be represented with a low number of bits. The selection of this signal is typically based on an exhaustive search procedure, in which for each prototype excitation the corresponding speech signal is constructed. The average mean-squared error between the original and the reconstructed signal is used as a criterion to determine the best choice of Lhe excitation signal. In this paper, different excitation signals are discussed, as well as procedures for determining the various coder parametsrs. In addition, the paper discusses some recently proposed speech coding standards, which are based on analysis-by-synthesis techniques.