The integration of digital voice with data in a common packet-switched network system offers a number of potential benefits, including reduced systems cost through sharing of switching and transmission resources, flexible internetworking among systems utilizing different transmission media, and enhanced services for users requiring access to both voice and data communications. Issues which it has been necessary to address in order to realize these benefits include reconstitution of speech from packets arriving at nonuniform intervals, maximization of packet speech multiplexing efficiency, and determination of the implementation requirements for terminals and switching in a large-scale packet voice/data system. A series of packet speech systems experiments to address these issues has been conducted under the sponsorship of the Defense Advanced Research Projects Agency (DARPA). In the initial experiments on the ARPANET, the basic feasibility of speech communication on a store-and-forward packet network was demonstrated. Techniques were developed for reconstitution of speech from packets, and protocols were developed for call setup and for speech transport. Later speech experiments utilizing the Atlantic packet satellite network (SATNET) led to the development of techniques for efficient voice conferencing in a broadcast environment, and for internetting speech between a store-and-forward net (ARPANEI) and a broadcast net (SATNET). Large-scale packet speech multiplexing experiments could not be carried out on ARPANET or SATNET where the network link capacities severely restrict the number of speech users that can be accommodated. However, experiments are currently being carried out using a wide-band satellite-based packet system designed to accommodate a sufficient number of simultaneous users to support realistic experiments in efficient statistical multiplexing. Key developments to date associated with the wide-band experiments have been 1) techniques for internetting via voice/data gateways from a variety of local access networks (packet cable, packet radio, and circuit-switched) to a long-haul broadcast satellite network and 2) compact implementations of packet voice terminals with full protocol and voice capabilities. Basic concepts and issues associated with packet speech systems are described. Requirements and techniques for speech processing, voice protocols, packetization and reconstitution, conferencing, and multiplexing are discussed in the context of a generic packet speech system configuration. Specific experimental configurations and key packet speech results on the ARPANET, SATNET, and wide-band system are reviewed.

Experience with Speech Communication in Packet Networks

A speech recognition system extracts feature parameters from a speech waveform, determines phonemic features using the parameters and encoding segments of the speech waveform, determines the starting and terminal ends of a syllable part from a time series of the encoded segments, extracts the syllable part based on the determined starting and terminal ends and then generating a pattern of the syllable part, and recognizes an input speech through the recognition of each syllable by way of pattern matching of the generated pattern.

Recognition of continuous speech

Analytic phonetic processing in speech recognition usually results in segmentation and labelling and is followed by lexical matching based on sequences of phonetic labels. Segmentation and labelling are impaired by coarticulation effects and imperfect syllabication. Matching is complicated by missed, extraneous, and mislabelled segments. This paper describes an approach to phonetic-based analysis which minimizes the difficulties just mentioned. Phonetic word verification permits an evaluation of phonetic similarity of incoming speech with prestored lexical entries. The comparison is based on acoustic parameter values (rather than segment labels). This allows the evaluation to be phone-specific and context-dependent, thus accommodating naturally for coarticulation effects. It also permits scores for each phone to be gradient at the acoustic level, avoiding the difficulties of missed and extraneous phonetic segments. Because the approach is predictive (top-down), syllable-internal phonetic analysis can be performed where syllabication is imperfect. Finally, the approach naturally accommodates powerful transitional and durational constraints.

Phonetic word verification

Reconnaissance de la parole continue

A system for the recognition of spoken phrases is described The recognizer assumes that the input utterance contains one of a known set of allowable phrases, which may be spoken within a longer carrier sentence Analysis is performed on a syllable-by-syllable basis with only the strong syllables considered in the recognition process Each strong syllable is represented in terms of a set of distinguishing acoustic measurements taken at time points in and around the syllable nucleus Phrases are represented as sequences of strong syllables All parameters used in recognition are derived from LPC coefficients Input speech is limited to 33 kHz upper frequency Recognition is completed within 1-3 s after the utterance is spoken An interactive training facility allows flexible composition of key phrase sets Testing was performed for a number of phrase sets each containing ten or fewer phrases, and included equal numbers of talkers used in training and talkers not used in training Average phrase recognition accuracy was 95 percent when parameters were derived from unquantized (ie, 16-bit) LPC coefficients and 90 percent when the LPC coefficients were transmitted to the recognizer across the ARPA network at 3500 bits/s The recognizer has been incorporated into a user interface system where the parameters required to set up a point-to-point ARPANET voice connection can be established remotely by voice

A phrase recognizer using syllable-based acoustic measurements

A system for the recognition of spoken phrases is described. The input speech is filtered to 3.3 KHz (approximating telephone bandwidth), and parameters are computed while the utterance is spoken. The remaining time necessary to produce a result is generally less than the duration of the input utterance. The recognizer assumes that the input utterance contains one of a known set of key phrases; the phrase is allowed to be included within a more or less arbitrary carrier sentence. Analysis is performed on a syllable-by-syllable basis with only the strong syllables considered in the recognition process. An interactive training facility allows flexible composition of key phrase sets. Testing has been performed for a few phrase sets, each containing less than twenty phrases. Talkers used in the training and talkers not used in the training tested the system. The phrase recognition accuracy was 92% for each group of talkers. The recognizer has been used successfully to retrieve messages from a remote computer by voice.

C. Weinstein

Papers

A phrase recognizer using syllable-based acoustic measurements

A real-time phrase recognizer using telephone bandwidth speech