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.

Robust recognition of loud and Lombard speech in the fighter cockpit environment

Abstract: The major goal of this research is to reduce the discrepancy in recognition performance between normal and abnormal speech, given that reference templates were derived only from normal speech. A method is devised that uses the differences in spectral slope between linear predictive coding log magnitude spectra to weight the point-by-point energy differences between the spectra. The distances of all reference tokens of like phonemes are combined to form a smallest cumulative distance (SCD) method. When SCD is combined with the method of slope-dependent weighting (SDW), the most significant success is obtained. In terms of error rates for a fixed phoneme vector length of five, SDW+SCD is found to reduce the difference in error rate between normal and abnormal speech by approximately 50%. >

Natural sounding TTS based on syllable-like units

Abstract: In this work we describe a new “syllable-like” speech unit that is suitable for concatenative speech synthesis. These units are automatically generated using a group delay based segmentation algorithm and acoustically correspond to the form C*VC* (C: consonant, V: vowel). The effectiveness of the unit is demonstrated by synthesizing natural-sounding speech in Tamil, a regional Indian language. Significant quality improvement is obtained if bisyllable units are also used, rather than just monosyllables, with results far superior to the traditional diphone-based approach. An important advantage of this approach is the elimination of prosody rules. Since ƒ 0 is part of the target cost, the unit selection procedure chooses the best unit from among the many candidates. The naturalness of the synthesized speech demonstrates the effectiveness of this approach.

Speech coding via speech recognition and synthesis based on pre-enrolled phonetic tokens

Abstract: A speech coding system, responsive to an input speech signal provided by a system user, comprises: a speech coding portion including a speech recognition system responsive to the input speech signal and having a word vocabulary associated therewith, the speech recognition system recognizing the input speech signal in accordance with the vocabulary and generating phonetic tokens, such as at least one sequence of lefemes, representative of the input speech signal; a channel, responsive to the at least one sequence of lefemes, for transmitting and/or storing the at least one sequence of lefemes; and a speech synthesizing portion, responsive to the transmitted/stored sequence of lefemes, for generating a synthesized speech signal which is representative of the input speech signal provided by the system user using the at least one sequence of lefemes The speech recognition system preferably generates acoustic parameters from the input speech signal which include voice characteristics of the system user The speech coding system also preferably comprises a labeler which processes the input speech signal including words uttered by the system user which are not in the word vocabulary associated with the speech recognition system, the labeler generating phonetic tokens, such as at least one sequence of lefemes, optimally representative of the input speech signal The sequence of lefemes from the labeler and the speech recognition portion are compared, for each speech segment, and the sequence most similar to the input speech is selected for transmission/storage The speech synthesizing portion of the system preferably performs speech synthesis using pre-enrolled phonetic sub-units or tokens

A noise reduction preprocessor for mobile voice communication

Abstract: We describe a speech enhancement algorithm which leads to significant quality and intelligibility improvements when used as a preprocessor to a low bit rate speech coder. This algorithm was developed in conjunction with the mixed excitation linear prediction (MELP) coder which, by itself, is highly susceptible to environmental noise. The paper presents novel as well as known speech and noise estimation techniques and combines them into a highly effective speech enhancement system. The algorithm is based on short-time spectral amplitude estimation, soft-decision gain modification, tracking of the a priori probability of speech absence, and minimum statistics noise power estimation. Special emphasis is placed on enhancing the performance of the preprocessor in nonstationary noise environments.