The development of the MIT Lisp-machine based speech research workstation

Zue, Victor W.; Cyphers, D. Scott; Kassel, Robert H.; Kaufman, David H.; Leung, Hoi Yan; Randolph, Mark A.; Seneff, Stephanie; Unverferth, J.; Wilson, Todd

doi:10.1109/icassp.1986.1169063

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Segmentation and labeling of the waveforms was performed by the author with the help of playback and displays of several attributes including LPC and wide-band spectra, the speech signal and various bandlimited energy waveforms (Cyphers, 1985;Shipman, 1982;Zue et al, 1986). The Merriam-Webster Pocket dictionary provided a baseline phonemic transcription of the words.…”

Section: Initial Processingmentioning

confidence: 99%

Acoustic measures for linguistic features distinguishing the semivowels /w j r l/ in American English

Espy‐Wilson

1992

The Journal of the Acoustical Society of America

113

View full text Add to dashboard Cite

Acoustic properties related to the linguistic features which characterize the semivowels in American English were quantified and analyzed statistically. The features can be divided into those which separate the semivowels from other sounds and those which distinguish among the semivowels. The features of interest are sonorant, syllabic, consonantal, high, back, front, and retroflex. Acoustic correlates of these features were investigated in this study of the semivowels. The acoustic correlates, which are based on relative measures, were tested on a corpus of 233 polysyllabic words, each of which was spoken once by two males and two females. For the most part, the appropriate distinctions are made by the chosen acoustic properties for features. However, for each property, there was some overlap in the acoustic correlates of features for the sounds being distinguished. An examination of the sounds in the overlap regions reveals that their surface manifestation varies substantially from the canonical form. In large part, the observed variability can be explained in terms of changes due to feature spreading and lenition.

show abstract

Section: Initial Processingmentioning

confidence: 99%

Acoustic measures for linguistic features distinguishing the semivowels /w j r l/ in American English

Espy‐Wilson

1992

The Journal of the Acoustical Society of America

113

View full text Add to dashboard Cite

show abstract

“…The first author developed such a tool [11] in 1986 inspired by SPIRE [12,13] which promoted spectrogram reading research [14,15]. The developed tool consisted of 25,000 lines of Pascal code.…”

Section: Background and Motivationmentioning

confidence: 99%

Interactive tools for making vocoder-based signal processing accessible: Flexible manipulation of speech attributes for explorational research and education

Kawahara,

Morise

2024

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

show abstract

“…There are several existing tools geared towards the development of human language technologies. In the mid-eighties our group developed SPIRE [1], a set of Lisp-machine based signal analysis and display tools that enjoyed limited distribution. Another speech-related tool is the ISP package designed by Kopec [2].…”

Section: Motivationmentioning

confidence: 99%

SAPPHIRE: an extensible speech analysis and recognition tool based on tcl/tk

Hetherington¹,

McCandless²

1996

4th International Conference on Spoken Language Processing (ICSLP 1996)

View full text Add to dashboard Cite

The SAPPHIRE system is a powerful, extensible, object-oriented toolkit allowing researchers to rapidly build and configure customized speech analysis tools. Implemented in Tcl/Tk and C, the current version of SAPPHIRE provides a wide range of functionality, including the ability to configure and run the SUMMIT speech recognition system. We now use SAPPHIRE widely in almost all aspects of our speech analysis and recognition research.

show abstract

The development of the MIT Lisp-machine based speech research workstation

Cited by 6 publications

References 3 publications

Acoustic measures for linguistic features distinguishing the semivowels /w j r l/ in American English

Acoustic measures for linguistic features distinguishing the semivowels /w j r l/ in American English

Interactive tools for making vocoder-based signal processing accessible: Flexible manipulation of speech attributes for explorational research and education

SAPPHIRE: an extensible speech analysis and recognition tool based on tcl/tk

Contact Info

Product

Resources

About