Speech recognition in which the log probabilities of the null and alternative hypothesis are computed for an input speech sample by comparison with specific stored speech vocabularies/grammars and with general speech characteristics. The difference in probabilities is normalized by the magnitude of the null hypothesis to derive a likelihood factor which is compared with a rejection threshold that is utterance-length dependent. Advantageously, a high-order polynomial representation of the rejecti...

A speech recognition feature extractor for extracting speech features from a speech signal, comprising: a time-to-frequency domain transformer (FFT) for generating spectral magnitude values in the frequency domain from the speech signal; a frequency domain filtering block (Mel) for generating a sub-band value relating to spectral magnitude values of a certain frequency sub-band; a compression block (LOG) for compressing said sub-band values; a transformation block (DCT) for obtaining a set of de...

A method of encoding a frame in a communication network using multiple codec modes, wherein the frame encoded by each codec mode is represented by multiple parameters. The method includes at least one stage, wherein the stage includes the steps of selecting one group from multiple groups of codec modes, wherein each group includes at least one codec mode and is arranged to have a common parameter characteristic. The method further includes encoding the frame with one of the codec modes from the ...

An excitation quantizer 60 in a speech encoder includes a divider, which divides M pulses representing in combination a speech signal into groups each of L pulses, L being smaller than M. The amplitude of pulses, i.e., L pulses as each unit, is quantized, using spectral parameter. The quantization is executed on at least one quantization candidate, which is selected through distortion evaluation made through addition of the evaluation value based on an adjacent group quantization candidate outpu...

A post-processor 317 and method substantially for enhancing synthesised speech is disclosed. The post-processor 317 operates on a signal ex(n) derived from an excitation generator 211 typically comprising a fixed code book 203 and an adaptive code book 204, the signal ex(n) being formed from the addition of scaled outputs from the fixed code book 203 and adaptive code book 204. The post-processor operates on ex(n) by adding to it a scaled signal pv(n) derived from the adaptive code book 204. A g...

The present invention relates to the management of voice data. Voice messages left on a recipient's answerphone or delivered via a voicemail system are a popular form of person-to-person communication. Such voice messages are quick to generate for the sender but are relatively difficult to review for the recipient; speech is slow to listen to and, unlike inherently visual forms of messages such as electronic mail or handwritten notes, cannot be quickly scanned for the relevant information. The p...

A computer system has a power-down mode to conserve energy. The computer system includes a speech transducer for capturing speech; a low-energy consuming power-up indicator coupled to said speech transducer, said power-up indicator detecting speech directed at said speech transducer and asserting a wake-up signal to a powered-down processor; and a voice recognizer coupled to said speech transducer and said wake-up signal, said voice recognizer waking up from the power-down mode when said wake-up...

In a system in which a plurality of previously recorded waveforms corresponding to phonetic elements separately picked up from natural voice and having a pitch length, are connected to form any required speech, the degradation in the quality of the synthesized speech due to the discontinuity in the waveform of the synthesized speech is prevented by so controlling the period of reading out each phonetic element as to change the period stepwise at intervals of several phonetic elements (i.e., pitc...

A speech network for performing both the hybrid and d-c line voltage regulation functions includes a high gain voltage controlled current source with feedback for compensating for the shunting effect of relatively low impedance d-c power supply circuits across the line. The network can be fabricated by integrated circuit techniques.

To differentiate speech on an incoming line from control tones, such as engaged tone signals, busy signals, or other non-speech frequencies, so that associated recording apparatus will not be activated by non-speech frequencies but will be activated by speech frequencies, the incoming signal is fed to a discriminator which discriminates on the basis of time dependent frequency variations (i.e. in the intervals between changes in frequency which in the case of speech are different and much shorte...