MX9702521A - Metodo y aparato para un sistema de recocimiento de lenguaje mejorado. - Google Patents
Metodo y aparato para un sistema de recocimiento de lenguaje mejorado.Info
- Publication number
- MX9702521A MX9702521A MX9702521A MX9702521A MX9702521A MX 9702521 A MX9702521 A MX 9702521A MX 9702521 A MX9702521 A MX 9702521A MX 9702521 A MX9702521 A MX 9702521A MX 9702521 A MX9702521 A MX 9702521A
- Authority
- MX
- Mexico
- Prior art keywords
- language
- word
- model
- machines
- language recognition
- Prior art date
Links
- 230000008520 organization Effects 0.000 abstract 1
- 230000035945 sensitivity Effects 0.000 abstract 1
- 230000007704 transition Effects 0.000 abstract 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/193—Formal grammars, e.g. finite state automata, context free grammars or word networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/19—Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
- G10L15/197—Probabilistic grammars, e.g. word n-grams
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
- Character Discrimination (AREA)
Abstract
La presente invencion se refiere a métodos y aparatos para un modelo de lenguaje y sistemas de reconocimiento de lenguaje. El método utiliza una pluralidad de máquinas de estado finito probabilísticas, que tienen la capacidad por reconocer un par de secuencias, una secuencia se explora hacia la izquierda, la otra se explora hacia la derecha. Cada palabra en el léxico del modelo de lenguaje se asocia con una o más de estas máquinas, que modelan las relaciones semánticas entre la palabra y otras palabras. Transiciones de máquina crean fases a partir de un conjunto de hipotesis de sartas de palabras y calculan de manera incremental los costos referentes a la probabilidad que estas frases representan el lenguaje a reconocer. Las máquinas de cabecera de léxico en cascada utilizadas en los métodos y aparatos, capturan las asociaciones estructurales implícitas en la organizacion jerárquica de un a frase, resultando en un modelo de lenguaje y sistemas de reconocimiento de lenguaje que combinan la sensibilidad de léxico de modelos N-Gram, con las propiedades estructurales de la gramática de dependencia.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/631,874 US5870706A (en) | 1996-04-10 | 1996-04-10 | Method and apparatus for an improved language recognition system |
US08631874 | 1996-04-10 |
Publications (2)
Publication Number | Publication Date |
---|---|
MX9702521A true MX9702521A (es) | 1997-10-31 |
MXPA97002521A MXPA97002521A (es) | 1998-07-03 |
Family
ID=
Also Published As
Publication number | Publication date |
---|---|
CA2198306C (en) | 2001-05-01 |
EP0801378B1 (en) | 2002-12-18 |
DE69717899T2 (de) | 2003-08-21 |
EP0801378A2 (en) | 1997-10-15 |
US5870706A (en) | 1999-02-09 |
DE69717899D1 (de) | 2003-01-30 |
EP0801378A3 (en) | 1998-09-30 |
CA2198306A1 (en) | 1997-10-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2198306A1 (en) | Method and apparatus for an improved language recognition system | |
Bahl et al. | A maximum likelihood approach to continuous speech recognition | |
Jelinek | Statistical methods for speech recognition | |
US7072826B1 (en) | Language conversion rule preparing device, language conversion device and program recording medium | |
WO2000033211A3 (en) | Automatic segmentation of a text | |
EP0867858A3 (en) | Pronunciation generation in speech recognition | |
EP0874353A3 (en) | Pronunciation generation in speech recognition | |
ATE203119T1 (de) | Spracherkennungssystem für sprachen mit zusammengesetzten wörtern | |
Riley et al. | Automatic generation of detailed pronunciation lexicons | |
Hakkinen et al. | N-gram and decision tree based language identification for written words | |
Kirchhoff et al. | Novel speech recognition models for Arabic | |
Chen et al. | Discriminative training on language model | |
White | Natural language understanding and speech recognition | |
Ananthakrishnan et al. | Improved speech recognition using acoustic and lexical correlates of pitch accent in a n-best rescoring framework | |
CN110942767A (zh) | 一种asr语言模型识别标注与优化方法及其装置 | |
Ying et al. | An RNN-based algorithm to detect prosodic phrase for Chinese TTS | |
Black et al. | Analysis of unknown words through morphological decomposition | |
JP3686934B2 (ja) | 異種環境音声データの音声検索方法及び装置 | |
Heeman et al. | Incorporating POS tagging into language modeling | |
Kita et al. | Processing unknown words in continuous speech recognition | |
JP2965529B2 (ja) | 音声認識装置 | |
Maučec et al. | Modelling highly inflected Slovenian language | |
Zong et al. | Chinese utterance segmentation in spoken language translation | |
JPS6229796B2 (es) | ||
Pieraccini et al. | Factorization of language constraints in speech recognition |