Intelligent Speech Analyser

 Intelligent Speech Analyser (ISA) is a speech and voice analyzer developed in Finland.

1980s Intelligent Speech Analyser™ (ISA) system. On the left there is a Macintosh SE/30 with a hard drive. On the right there is an ISA signal computer that includes a Texas universal 16-bit TMS32010 signal processor and a separate large 16-bit signal memory. Sony 16-bit 2-channel converters are connected to the signal computer. ISA measures frequencies with scales: hertz, Bark, ERB, mel, Koenig, octave, semitone, semitone/100 and semitone/1000.^[1][2][3]

Intelligent Speech Analyser™ (ISA)

The first presentation of the Intelligent Speech Analyser (ISA)Edit

The first presentation of the Intelligent Speech Analyser (ISA) developed by Raimo Olavi Toivonen took place in January 1987 at the Finnish Phonetics Meeting at Jyväskylä University.^[3] The development work started in 1985 and has continued since then.^[1][2]

Articles whose some results have been obtained using ISAEdit

In 100 academic theses, 27 of which are academic dissertations, spoken language have been studied with the help of the ISA developed by Toivonen. There are a total of almost 500 publications. Using ISA, 17 spoken languages have been academically researched and written articles with 15 languages. These 17 spoken languages are Finnish, Finnish dialects, Finno-Ugric, Finland Swedish, Swedish, Estonian, Icelandic, Hungarian, Polish, Czech, German in various European countries, Russian, English language in different countries, French, Greek in Athens, Crete and Cyprus, Portuguese, Spanish in Spain, South America, North Africa.^{[1][2][4][5][6][7][8][9][10][11]}

Using ISA, scientific publications were published in the following areas:

• Phonetics,^{[7][12][13][14][15]}
  
• Measurement of formants of human voice (F1, F2, F3 und F4),^[16][17]
  
• Bark Scale Formant Charts of human voice,^{[16][17][7][12][13][14][8][18][19]}
  
• Measurement of the fundamental frequency of human voice (F0),^{[9][10][20][21][7]}
  
• Measurement of the sound pressure level of human voice (SPL),^{[4][5][22][23][24]}
  
• Measurement of the Computer Voice Field of human voice (CVF),^{[9][10][25][26][27][28][29][30][31]}
  
• Segmentation of the human voice,^{[32][33][34][35]}
  
• FFT spectrum of human voice,^{[16][17][36][15][7]}
  
• FFT spektrogram of human voice,^[16][17][7]
  
• FFT spectral series of human voice,^[16][17]
  
• LPC spectrum of human voice,^[16][17][7]
  
• LPC spektrogram of human voice,^[16][17]
  
• LPC spectral series of human voice,^[16][17][7]
  
• Cepstrum of human voice,^[16][17]
  
• Cepstral series of human voice,^[16][17]
  
• Auditory spektrum of human voice,^[15]
  
• Auditory spektrogram of human voice,^[15]
  
• Auditory spectral series of human voice,^[15]
  
• Phonetogram of the human voice,^[36]
  
• Jitter, shimmer, S/N ratio of the human voice,^{[37][38][39][36]}
  
• F0 distribution of the human voice on the semitone scale,^{[37][38][39][36]}
  
• Measurement of the Long-Term Average Spectrum of human voice (LTAS),^{[4][5][22][23][24][36]}
  
• Alpha ratio of Long-Term Average Spectrum of human voice,^{[4][5][22][23][24][36]}
  
• L0, L1, L2, L3 L4, L1-L0 of Long-Term Average Spectrum of human voice,^{[4][5][22][23][24][36]}
  
• Leq, Equivalent continuous sound level of human voice,^{[4][5][22][23][24][36]}
  
• Speech research on a loudness scale (Sone scale),^[32][33][34]
  
• Spectral properties of a good human voice,^{[4][5][22][23][24]}
  
• Teacher's voice,^{[40][41][42][43][37][44]}
  
• Radio Speech,^[45]
  
• Emotions in the voice,^[46][47]
  
• Speech prosody,^{[7][48][32][49]}
  
• Speaker recognition,^[50][51][52]
• Speech synthesis by Synte 2 text-to-speech synthesizer, SPL1 research speech synthesizer and ISA,^[35][53]
• Brain research by Synte 2 text-to-speech synthesizer, SPL1 research speech synthesizer and ISA,^{[54][55][56][57][58][59]}
• Speech therapy,^[1][2]
  
• Vocology,^{[36][60][61][62][63]}
  
• Phonology,^[8]
  
• Psychoacoustics,^[16][17]
  
• Phoniatrics,^{[9][10][25][26][27][28][29][30][31]}
  
• Audiology,^[64][65]
  
• Musical instrument research.^{[11][66][67][68]}

This article uses material from the Wikipedia article  Metasyntactic variable, which is released under the  Creative Commons Attribution-ShareAlike 3.0 Unported License.