Document (#39661)

Author
Stolcke, A.
Title
Linguistic knowledge and empirical methods in speech recognition
Source
AI magazine. 18(1997) no.4, S.25-31
Year
1997
Abstract
Reviews how state-of-the-art speech recognition systems combine statistical modelling, linguistic knowledge, and machine learning to achieve their performance and points out some of the research issues in the field
Footnote
Contribution to a special section reviewing recent research in empirical methods in speech recognition, syntactic parsing, semantic processing, information extraction and machine translation
Theme
Computerlinguistik

Similar documents (content)

  1. Multilingual information management : current levels and future abilities. A report Commissioned by the US National Science Foundation and also delivered to the European Commission's Language Engineering Office and the US Defense Advanced Research Projects Agency, April 1999 (1999) 0.45
    0.4546961 = sum of:
      0.4546961 = product of:
        0.9093922 = sum of:
          0.01365886 = weight(abstract_txt:research in 68) [ClassicSimilarity], result of:
            0.01365886 = score(doc=68,freq=2.0), product of:
              0.05589613 = queryWeight, product of:
                1.0022819 = boost
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.017650712 = queryNorm
              0.24436146 = fieldWeight in 68, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.017188486 = weight(abstract_txt:systems in 68) [ClassicSimilarity], result of:
            0.017188486 = score(doc=68,freq=2.0), product of:
              0.06515242 = queryWeight, product of:
                1.0820923 = boost
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.017650712 = queryNorm
              0.2638196 = fieldWeight in 68, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.02155574 = weight(abstract_txt:some in 68) [ClassicSimilarity], result of:
            0.02155574 = score(doc=68,freq=2.0), product of:
              0.07576712 = queryWeight, product of:
                1.1669155 = boost
                3.6785707 = idf(docFreq=3049, maxDocs=44421)
                0.017650712 = queryNorm
              0.2844999 = fieldWeight in 68, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.6785707 = idf(docFreq=3049, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.021782314 = weight(abstract_txt:methods in 68) [ClassicSimilarity], result of:
            0.021782314 = score(doc=68,freq=1.0), product of:
              0.096128345 = queryWeight, product of:
                1.3143916 = boost
                4.1434727 = idf(docFreq=1915, maxDocs=44421)
                0.017650712 = queryNorm
              0.22659616 = fieldWeight in 68, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.1434727 = idf(docFreq=1915, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.02768826 = weight(abstract_txt:field in 68) [ClassicSimilarity], result of:
            0.02768826 = score(doc=68,freq=1.0), product of:
              0.1128009 = queryWeight, product of:
                1.4238207 = boost
                4.4884357 = idf(docFreq=1356, maxDocs=44421)
                0.017650712 = queryNorm
              0.24546133 = fieldWeight in 68, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.4884357 = idf(docFreq=1356, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.03019038 = weight(abstract_txt:performance in 68) [ClassicSimilarity], result of:
            0.03019038 = score(doc=68,freq=1.0), product of:
              0.11949815 = queryWeight, product of:
                1.465479 = boost
                4.619759 = idf(docFreq=1189, maxDocs=44421)
                0.017650712 = queryNorm
              0.25264308 = fieldWeight in 68, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.619759 = idf(docFreq=1189, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.08988823 = weight(abstract_txt:machine in 68) [ClassicSimilarity], result of:
            0.08988823 = score(doc=68,freq=4.0), product of:
              0.15579876 = queryWeight, product of:
                1.6733278 = boost
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.017650712 = queryNorm
              0.57695085 = fieldWeight in 68, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.04833292 = weight(abstract_txt:points in 68) [ClassicSimilarity], result of:
            0.04833292 = score(doc=68,freq=1.0), product of:
              0.16353503 = queryWeight, product of:
                1.7143695 = boost
                5.4043584 = idf(docFreq=542, maxDocs=44421)
                0.017650712 = queryNorm
              0.29555085 = fieldWeight in 68, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.4043584 = idf(docFreq=542, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.05225085 = weight(abstract_txt:statistical in 68) [ClassicSimilarity], result of:
            0.05225085 = score(doc=68,freq=1.0), product of:
              0.17225732 = queryWeight, product of:
                1.7594943 = boost
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.017650712 = queryNorm
              0.3033302 = fieldWeight in 68, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.24245113 = weight(abstract_txt:recognition in 68) [ClassicSimilarity], result of:
            0.24245113 = score(doc=68,freq=3.0), product of:
              0.41863403 = queryWeight, product of:
                3.8791027 = boost
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.017650712 = queryNorm
              0.5791482 = fieldWeight in 68, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
          0.344405 = weight(abstract_txt:speech in 68) [ClassicSimilarity], result of:
            0.344405 = score(doc=68,freq=3.0), product of:
              0.52901095 = queryWeight, product of:
                4.360601 = boost
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.017650712 = queryNorm
              0.65103567 = fieldWeight in 68, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.0546875 = fieldNorm(doc=68)
        0.5 = coord(11/22)
    
  2. Brill, E.: ¬An overview of empirical natural language processing (1997) 0.43
    0.42566785 = sum of:
      0.42566785 = product of:
        1.1705866 = sum of:
          0.02207605 = weight(abstract_txt:research in 4249) [ClassicSimilarity], result of:
            0.02207605 = score(doc=4249,freq=1.0), product of:
              0.05589613 = queryWeight, product of:
                1.0022819 = boost
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.017650712 = queryNorm
              0.39494774 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.02778079 = weight(abstract_txt:systems in 4249) [ClassicSimilarity], result of:
            0.02778079 = score(doc=4249,freq=1.0), product of:
              0.06515242 = queryWeight, product of:
                1.0820923 = boost
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.017650712 = queryNorm
              0.42639688 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.07041107 = weight(abstract_txt:methods in 4249) [ClassicSimilarity], result of:
            0.07041107 = score(doc=4249,freq=2.0), product of:
              0.096128345 = queryWeight, product of:
                1.3143916 = boost
                4.1434727 = idf(docFreq=1915, maxDocs=44421)
                0.017650712 = queryNorm
              0.7324694 = fieldWeight in 4249, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                4.1434727 = idf(docFreq=1915, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.07463391 = weight(abstract_txt:learning in 4249) [ClassicSimilarity], result of:
            0.07463391 = score(doc=4249,freq=1.0), product of:
              0.12590945 = queryWeight, product of:
                1.5042783 = boost
                4.7420692 = idf(docFreq=1052, maxDocs=44421)
                0.017650712 = queryNorm
              0.59275866 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.7420692 = idf(docFreq=1052, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.098506205 = weight(abstract_txt:empirical in 4249) [ClassicSimilarity], result of:
            0.098506205 = score(doc=4249,freq=1.0), product of:
              0.15149905 = queryWeight, product of:
                1.6500762 = boost
                5.2016807 = idf(docFreq=664, maxDocs=44421)
                0.017650712 = queryNorm
              0.6502101 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2016807 = idf(docFreq=664, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.1027294 = weight(abstract_txt:machine in 4249) [ClassicSimilarity], result of:
            0.1027294 = score(doc=4249,freq=1.0), product of:
              0.15579876 = queryWeight, product of:
                1.6733278 = boost
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.017650712 = queryNorm
              0.6593724 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.31995252 = weight(abstract_txt:recognition in 4249) [ClassicSimilarity], result of:
            0.31995252 = score(doc=4249,freq=1.0), product of:
              0.41863403 = queryWeight, product of:
                3.8791027 = boost
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.017650712 = queryNorm
              0.7642774 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
          0.45449668 = weight(abstract_txt:speech in 4249) [ClassicSimilarity], result of:
            0.45449668 = score(doc=4249,freq=1.0), product of:
              0.52901095 = queryWeight, product of:
                4.360601 = boost
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.017650712 = queryNorm
              0.8591442 = fieldWeight in 4249, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.125 = fieldNorm(doc=4249)
        0.36363637 = coord(8/22)
    
  3. Jurafsky, D.; Martin, J.H.: Speech and language processing : ani ntroduction to natural language processing, computational linguistics and speech recognition (2009) 0.31
    0.31414777 = sum of:
      0.31414777 = product of:
        0.98732156 = sum of:
          0.017362993 = weight(abstract_txt:systems in 2081) [ClassicSimilarity], result of:
            0.017362993 = score(doc=2081,freq=1.0), product of:
              0.06515242 = queryWeight, product of:
                1.0820923 = boost
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.017650712 = queryNorm
              0.26649806 = fieldWeight in 2081, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.411175 = idf(docFreq=3984, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.046646196 = weight(abstract_txt:learning in 2081) [ClassicSimilarity], result of:
            0.046646196 = score(doc=2081,freq=1.0), product of:
              0.12590945 = queryWeight, product of:
                1.5042783 = boost
                4.7420692 = idf(docFreq=1052, maxDocs=44421)
                0.017650712 = queryNorm
              0.37047416 = fieldWeight in 2081, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.7420692 = idf(docFreq=1052, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.061566383 = weight(abstract_txt:empirical in 2081) [ClassicSimilarity], result of:
            0.061566383 = score(doc=2081,freq=1.0), product of:
              0.15149905 = queryWeight, product of:
                1.6500762 = boost
                5.2016807 = idf(docFreq=664, maxDocs=44421)
                0.017650712 = queryNorm
              0.4063813 = fieldWeight in 2081, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.2016807 = idf(docFreq=664, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.06420588 = weight(abstract_txt:machine in 2081) [ClassicSimilarity], result of:
            0.06420588 = score(doc=2081,freq=1.0), product of:
              0.15579876 = queryWeight, product of:
                1.6733278 = boost
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.017650712 = queryNorm
              0.41210774 = fieldWeight in 2081, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.10556265 = weight(abstract_txt:statistical in 2081) [ClassicSimilarity], result of:
            0.10556265 = score(doc=2081,freq=2.0), product of:
              0.17225732 = queryWeight, product of:
                1.7594943 = boost
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.017650712 = queryNorm
              0.61281955 = fieldWeight in 2081, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.19997033 = weight(abstract_txt:recognition in 2081) [ClassicSimilarity], result of:
            0.19997033 = score(doc=2081,freq=1.0), product of:
              0.41863403 = queryWeight, product of:
                3.8791027 = boost
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.017650712 = queryNorm
              0.47767338 = fieldWeight in 2081, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
          0.4920071 = weight(abstract_txt:speech in 2081) [ClassicSimilarity], result of:
            0.4920071 = score(doc=2081,freq=3.0), product of:
              0.52901095 = queryWeight, product of:
                4.360601 = boost
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.017650712 = queryNorm
              0.9300509 = fieldWeight in 2081, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.078125 = fieldNorm(doc=2081)
        0.3181818 = coord(7/22)
    
  4. Lange, H.R.: Speech synthesis and speech recognition : tomorrow's human-computer interface? (1993) 0.29
    0.2925279 = sum of:
      0.2925279 = product of:
        1.6089034 = sum of:
          0.019316543 = weight(abstract_txt:research in 7223) [ClassicSimilarity], result of:
            0.019316543 = score(doc=7223,freq=1.0), product of:
              0.05589613 = queryWeight, product of:
                1.0022819 = boost
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.017650712 = queryNorm
              0.34557927 = fieldWeight in 7223, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.109375 = fieldNorm(doc=7223)
          0.06884399 = weight(abstract_txt:state in 7223) [ClassicSimilarity], result of:
            0.06884399 = score(doc=7223,freq=1.0), product of:
              0.13041858 = queryWeight, product of:
                1.5309774 = boost
                4.8262353 = idf(docFreq=967, maxDocs=44421)
                0.017650712 = queryNorm
              0.52786946 = fieldWeight in 7223, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.8262353 = idf(docFreq=967, maxDocs=44421)
                0.109375 = fieldNorm(doc=7223)
          0.39592102 = weight(abstract_txt:recognition in 7223) [ClassicSimilarity], result of:
            0.39592102 = score(doc=7223,freq=2.0), product of:
              0.41863403 = queryWeight, product of:
                3.8791027 = boost
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.017650712 = queryNorm
              0.945745 = fieldWeight in 7223, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.109375 = fieldNorm(doc=7223)
          1.1248219 = weight(abstract_txt:speech in 7223) [ClassicSimilarity], result of:
            1.1248219 = score(doc=7223,freq=8.0), product of:
              0.52901095 = queryWeight, product of:
                4.360601 = boost
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.017650712 = queryNorm
              2.1262734 = fieldWeight in 7223, product of:
                2.828427 = tf(freq=8.0), with freq of:
                  8.0 = termFreq=8.0
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.109375 = fieldNorm(doc=7223)
        0.18181819 = coord(4/22)
    
  5. Liu, X.; Croft, W.B.: Statistical language modeling for information retrieval (2004) 0.27
    0.27378732 = sum of:
      0.27378732 = product of:
        0.7529151 = sum of:
          0.009592455 = weight(abstract_txt:their in 5277) [ClassicSimilarity], result of:
            0.009592455 = score(doc=5277,freq=1.0), product of:
              0.0556419 = queryWeight, product of:
                3.1523883 = idf(docFreq=5161, maxDocs=44421)
                0.017650712 = queryNorm
              0.17239624 = fieldWeight in 5277, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                3.1523883 = idf(docFreq=5161, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.01365886 = weight(abstract_txt:research in 5277) [ClassicSimilarity], result of:
            0.01365886 = score(doc=5277,freq=2.0), product of:
              0.05589613 = queryWeight, product of:
                1.0022819 = boost
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.017650712 = queryNorm
              0.24436146 = fieldWeight in 5277, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                3.159582 = idf(docFreq=5124, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.03019038 = weight(abstract_txt:performance in 5277) [ClassicSimilarity], result of:
            0.03019038 = score(doc=5277,freq=1.0), product of:
              0.11949815 = queryWeight, product of:
                1.465479 = boost
                4.619759 = idf(docFreq=1189, maxDocs=44421)
                0.017650712 = queryNorm
              0.25264308 = fieldWeight in 5277, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.619759 = idf(docFreq=1189, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.03712059 = weight(abstract_txt:reviews in 5277) [ClassicSimilarity], result of:
            0.03712059 = score(doc=5277,freq=1.0), product of:
              0.13714881 = queryWeight, product of:
                1.5699834 = boost
                4.9491973 = idf(docFreq=855, maxDocs=44421)
                0.017650712 = queryNorm
              0.27065924 = fieldWeight in 5277, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.9491973 = idf(docFreq=855, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.044944115 = weight(abstract_txt:machine in 5277) [ClassicSimilarity], result of:
            0.044944115 = score(doc=5277,freq=1.0), product of:
              0.15579876 = queryWeight, product of:
                1.6733278 = boost
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.017650712 = queryNorm
              0.28847542 = fieldWeight in 5277, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.274979 = idf(docFreq=617, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.13824274 = weight(abstract_txt:statistical in 5277) [ClassicSimilarity], result of:
            0.13824274 = score(doc=5277,freq=7.0), product of:
              0.17225732 = queryWeight, product of:
                1.7594943 = boost
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.017650712 = queryNorm
              0.80253625 = fieldWeight in 5277, product of:
                2.6457512 = tf(freq=7.0), with freq of:
                  7.0 = termFreq=7.0
                5.5466094 = idf(docFreq=470, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.19796051 = weight(abstract_txt:recognition in 5277) [ClassicSimilarity], result of:
            0.19796051 = score(doc=5277,freq=2.0), product of:
              0.41863403 = queryWeight, product of:
                3.8791027 = boost
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.017650712 = queryNorm
              0.4728725 = fieldWeight in 5277, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.114219 = idf(docFreq=266, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
          0.28120548 = weight(abstract_txt:speech in 5277) [ClassicSimilarity], result of:
            0.28120548 = score(doc=5277,freq=2.0), product of:
              0.52901095 = queryWeight, product of:
                4.360601 = boost
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.017650712 = queryNorm
              0.53156835 = fieldWeight in 5277, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                6.8731537 = idf(docFreq=124, maxDocs=44421)
                0.0546875 = fieldNorm(doc=5277)
        0.36363637 = coord(8/22)